![[Search]](/static/images/search.gif){kind=small}
![[A-Z Index]](/static/images/az.gif){kind=small}
![[Contact]](/static/images/contact.gif){kind=small}
![[University of Cambridge]](/static/images/identifier2.gif){kind=small}
![[Talks.cam]](/static/images/talkslogosmall.gif)
Abbas Mammadov (University of Oxford).
Tuesday 24 March 2026, 15:00-16:30
Contact: Tomas Van Pottelbergh
0 upcoming talks View 1301 archived talks
Machine Learning Reading Group @ CUED
From Stochastic Interpolants to Flow Maps: Foundations, Fast Generation, and Applications to Weather & Climate Modeling
Machine Learning Reading Group @ CUED
Evolution Strategies at the Hyperscale
Machine Learning Reading Group @ CUED
Evolution Strategies at the Hyperscale
Machine Learning Reading Group @ CUED
Machine Learning on Tabular Data
Machine Learning Reading Group @ CUED
Rethinking aleatoric and epistemic uncertainty
Machine Learning Reading Group @ CUED
How does gradient descent work?
Machine Learning Reading Group @ CUED
Variational Inference: An Algorithm-Centric Perspective
Machine Learning Reading Group @ CUED
Neural Operators for Scientific Simulation
Machine Learning Reading Group @ CUED
A Tutorial on Algorithmic Information Theory in Modern ML
Machine Learning Reading Group @ CUED
Diffusion Language Models
Machine Learning Reading Group @ CUED
An Introduction to Stochastic Interpolants
Cambridge Statistics Clinic
Statistics Clinic Summer 2025 II
Machine Learning Reading Group @ CUED
The structure of curvature in neural networks
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Variational Uncertainty Decomposition for In-Context Learning
Machine Learning Reading Group @ CUED
Variational Uncertainty Decomposition for In-Context Learning
Machine Learning Reading Group @ CUED
Vision-language models (VLMs)
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Vision-language models (VLMs)
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Conditional Expectation and Machine Learning
Machine Learning Reading Group @ CUED
Evaluating and Regulating Foundation Models
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Out-of-context reasoning/learning in LLMs and its safety implications
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Learning to See the World in 3D
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
An Introduction to In-Context Learning
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
ML for Medium-Range Weather Forecasting
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Influence Functions
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Sampling with diffusion models
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Geometric Deep Learning for Structure-Based Drug Design
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Diffusion Models Beyond Mean Prediction
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Unpacking UKβs New AI Action Plan: Ambition versus Reality
β οΈ Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
An Introduction to Algorithmic Differentiation
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
An Introduction to Algorithmic Differentiation
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Foundation Models in Robotics
Machine Learning Reading Group @ CUED
Learning curve prediction for AutoML
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Learning curve prediction for AutoML
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
An Elementary Introduction to Sequential Monte Carlo Samplers
Machine Learning Reading Group @ CUED
Scalable Sampling Using Annealed Algorithms
Machine Learning Reading Group @ CUED
Are we making progress in unlearning?Β
Machine Learning Reading Group @ CUED
Natural Experiments in NLP and Where to Find Them
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Linear Attention for Efficient Transformers
Machine Learning Reading Group @ CUED
Task Alignment
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning @ CUED
Application of the optimal transport Gromov-Wasserstein problem to manifold learning and graph analysis
Machine Learning @ CUED
Application of the optimal transport Gromov-Wasserstein problem to manifold learning and graph analysis
Machine Learning @ CUED
Application of the optimal transport Gromov-Wasserstein problem to manifold learning and graph analysis
Machine Learning Reading Group @ CUED
A Light Introduction to Topological Data Analysis
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Mean Field Theory of NNs
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk
Machine Learning Reading Group @ CUED
Discussing the Stanford AI Report
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Discussing the Stanford AI Report
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
AI Control
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Neural likelihood-free inference
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
An Introduction to the Conjugate Gradient Method
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
An Introduction to Transformer Neural Processes
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning @ CUED
Consistent Validation for Predictive Methods in Spatial Settings
Machine Learning Reading Group @ CUED
Learning Symmetries in Neural Networks
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
GenCast: Diffusion-based ensemble forecasting for medium-range weather (or: How to ruin a numerical weather forecasterβs Christmas)
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Bayesian coresets
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Flow matching, stochastic interpolants and everything in between
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning @ CUED
Modern Bayesian Experimental Design
Machine Learning Reading Group @ CUED
Challenges of Regulating Increasingly Complicated Human-AI Collaborative Systems
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
A Poisson Process Model for Monte Carlo
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Learning Directed Acyclic Graphs (DAGs) With Continuous Optimization
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Deep Learning for Medium-Range Global Weather Prediction
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Learning linear models in-context with transformers
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Quasi-Monte Carlo: structure in the randomness for better sampling
Machine Learning @ CUED
Visit and talk by Jay McClelland: "Some thoughts on the differences between human and machine intelligence"
Machine Learning @ CUED
Compositional mathematics and automatic gradient descent
Machine Learning Reading Group @ CUED
Deciphering Batch Effects in Single-cell Transcriptomics with Concept Bottlenecks
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
SchrΓΆdinger bridges, diffusion and SDEs
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
The LLM Tidal Wave
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
The LLM Tidal Wave
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Game theory, distributional reinforcement learning, control and verification
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
On choosing the mass matrix for Hamiltonian Monte Carlo
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Reward Modelling
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning @ CUED
Convergence bounds for the Random Walk Metropolis algorithm - Perspectives from Isoperimetry
Machine Learning Reading Group @ CUED
Navigating the Future: Upcoming EU AI Regulation and its Potential Impact on the Field
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Learning-based multiscale modeling: computing, data science, and uncertainty quantification
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Neural Tangent Kernel
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning Reading Group @ CUED
No-regret Dynamics for Multi-agent Learning
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning Reading Group @ CUED
Scalable Approaches to Self-Supervised Learning using Spectral Analysis
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning Reading Group @ CUED
Physics-informed machine learning
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Causal Machine Learning
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
User Manipulation in Recommender Systems
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Machine Learning Reading Group @ CUED
Random Features for Kernel Approximation
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning Reading Group @ CUED
An Overview of Differential Privacy, Membership Inference Attacks, and Federated Learning
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning Reading Group @ CUED
Bayesian Neural Networks
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning Reading Group @ CUED
Offline Reinforcement Learning
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning Reading Group @ CUED
{PF}^2ES: Parallel Feasible Pareto Frontier Entropy Search for Multi-Objective Bayesian Optimization Under Unknown Constraints
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning @ CUED
Calls to F the Algorithm: Lessons from the 2020 Exam Debacle
Machine Learning Reading Group @ CUED
Scalable simulation and inference in non-Gaussian stochastic PDEs
Machine Learning @ CUED
Scalable simulation and inference in non-Gaussian stochastic PDEs
Machine Learning @ CUED
Measuring Alignment Between Perceptual Systems: An Analysis Through The Lens of Shared Invariances
Machine Learning Reading Group @ CUED
Information Geometry β Natural Gradient Descent
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning @ CUED
Gaussian processes, spectral analysis kernels and optimal transport
Machine Learning @ CUED
Deep Reinforcement Learning for Multi-Agent Interaction
Machine Learning Reading Group @ CUED
Predicting generalization of ML models.
β οΈ Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
Machine Learning @ CUED
Presenting Hawk-Eyeβs Skeletrack: Our machine learning approach to building a real time skeletal tracking system for sports, and how we're using it to shape the future of fan engagement
Machine Learning Reading Group @ CUED
A tutorial on diffusion models
Machine Learning Reading Group @ CUED
Benchmarking and evaluation in contemporary machine learning
Machine Learning Reading Group @ CUED
Advanced artificial agents intervene in the provision of reward
Machine Learning Reading Group @ CUED
Theory and Practice of Infinitely Wide Neural Networks - Guest Talk
Machine Learning Reading Group @ CUED
The unreasonable effectiveness of mathematics in large scale deep learning
Machine Learning Reading Group @ CUED
The role of meta-learning for few-shot classification
Machine Learning @ CUED
Noise-Aware Differentially Private Synthetic Data
Machine Learning Reading Group @ CUED
Benefits and Shortcomings of Assistance
Machine Learning @ CUED
Estimating RSV seasonality from pandemic disruptions: a modelling study
Machine Learning Reading Group @ CUED
Discussion: Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
Machine Learning Reading Group @ CUED
Discussion: Learning PAC-Bayes Priors for Probabilistic Neural Networks
Machine Learning Reading Group @ CUED
Rethinking evaluation for machine learning models
Machine Learning Reading Group @ CUED
Discussion: Bayesian Model Selection, the Marginal Likelihood, and Generalization
Machine Learning @ CUED
Beyond Conformal Prediction: Distribution-Free Uncertainty Quantification for Complex Machine Learning Tasks
Machine Learning Reading Group @ CUED
How close are these distributions? A brief introduction to statistical distances and divergences.
Machine Learning Reading Group @ CUED
Bests of ICLR
Machine Learning @ CUED
Graph neural network approach for decentralized multi-robot coordination
Machine Learning Reading Group @ CUED
Machine Learning with Quantum Computers
Machine Learning Reading Group @ CUED
Autoregressive Diffusion Models
Machine Learning Reading Group @ CUED
An Overview of AI Alignment
Machine Learning Reading Group @ CUED
The Bayesian Learning Rule for Adaptive AI
Machine Learning Reading Group @ CUED
Introduction to differential privacy
Machine Learning Reading Group @ CUED
Retrieval Augmented NLP
Machine Learning Reading Group @ CUED
Circuits and Interpretability
Machine Learning Reading Group @ CUED
Optimal Transport Metrics
Machine Learning Reading Group @ CUED
Learned Compression
Machine Learning Reading Group @ CUED
Diffusion and Score-based Generative Models
Machine Learning Reading Group @ CUED
AI Safety
Machine Learning Reading Group @ CUED
[Cancelled] Best of Neurips
Machine Learning Reading Group @ CUED
Energy-Based Models
Machine Learning Reading Group @ CUED
Deep Kernels
Machine Learning Reading Group @ CUED
Mean Field Theory of NN (postponed to March 2022)
Machine Learning Reading Group @ CUED
Representation Learning: A Causal Perspective
Machine Learning Reading Group @ CUED
Ethics, Integrity and Good Practice in ML
Machine Learning Reading Group @ CUED
Implicit Regularization in Deep Learning
Machine Learning Reading Group @ CUED
Planning Meeting + PI Presentations
Machine Learning Reading Group @ CUED
Towards Neuro-Causality: Relating Graph Neural Networks to Structural Causal Models
Machine Learning Reading Group @ CUED
CBL Alumni Talk - Task-specific routing of information in neural circuits via structured noise by Cristina Savin
Machine Learning Reading Group @ CUED
CBL Alumni Talk: Nonlinear filtering as a unifying principle in neuroscience by Jean-Pascal Pfister
Machine Learning Reading Group @ CUED
CBL Alumni Talk: Finale Doshi-Velez
Machine Learning Reading Group @ CUED
Pseudo-Points and State-Space Gaussian Processes
Machine Learning Reading Group @ CUED
CBL Alumni Talk: Latent Stochastic Differential Equations: An Unexplored Model Class.
Machine Learning Reading Group @ CUED
The Statistical Finite Element Method
Machine Learning Reading Group @ CUED
CBL Alumni Talk - Our Power as Technical Designers
Machine Learning Reading Group @ CUED
Best of ICLR
Machine Learning Reading Group @ CUED
CBL Alumni Talk: Accurate Gaussian Processes and how they can help Deep Learning
Machine Learning Reading Group @ CUED
An Introduction to PAC-Bayes
Machine Learning Reading Group @ CUED
Automated Augmented Conjugate Inference for Gaussian Processes
Machine Learning Reading Group @ CUED
CBL Alumni Talk: Examining Critiques in Bayesian Deep Learning
Machine Learning Reading Group @ CUED
Online Learning and Online Convex Optimisation
Machine Learning Reading Group @ CUED
Monte Carlo Gradient Estimation in Machine Learning
Machine Learning Reading Group @ CUED
Secondmind's research activities to make Gaussian Processes industry proof
Machine Learning Reading Group @ CUED
Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
Machine Learning Reading Group @ CUED
Gaussian Processes I have Known
Machine Learning Reading Group @ CUED
Causal Representation Learning
Machine Learning Reading Group @ CUED
Long-Range Transformers
Machine Learning Reading Group @ CUED
Inference in Stochastic Processes
Machine Learning Reading Group @ CUED
Fairness in AI
Machine Learning Reading Group @ CUED
Variational Bayes as Surrogate Regression
Machine Learning Reading Group @ CUED
Bayesian optimization / Gaussian Process Bandits
Machine Learning Reading Group @ CUED
Meta-reinforcement learning
Machine Learning Reading Group @ CUED
Best of NeurIPS
Machine Learning Reading Group @ CUED
Neural Processes
Machine Learning Reading Group @ CUED
Large-scale sequential experimentation
Machine Learning Reading Group @ CUED
Symmetries in Reinforcement Learning
Machine Learning Reading Group @ CUED
Gradient-based Hyperparameter Optimisation
Machine Learning Reading Group @ CUED
Best Papers from ICML 2020
Machine Learning @ CUED
Efficient and Structured Uncertainty: Challenges and Opportunities
Machine Learning Reading Group @ CUED
Active Learning
Machine Learning Reading Group @ CUED
Recent advances in the theory and applications of VAEs
Machine Learning Reading Group @ CUED
Best of ICLR 2020
Machine Learning Reading Group @ CUED
Differentiable Planning
Machine Learning Reading Group @ CUED
Recent Developments in Bayesian Deep Learning
Machine Learning Reading Group @ CUED
Strategic Classification
Machine Learning Reading Group @ CUED
Machine Learning on Sets
Machine Learning Reading Group @ CUED
Boltzmann Generators and Stochastic Normalizing Flows
Machine Learning Reading Group @ CUED
World Models
Machine Learning Reading Group @ CUED
Federated Learning
Machine Learning @ CUED
Game Playing Meets Game Theory: Strategic Learning from Simulated Play
Machine Learning Reading Group @ CUED
Self-Supervised Representation Learning
Machine Learning Reading Group @ CUED
Kernel Mean Embeddings
Machine Learning Reading Group @ CUED
Neural Tangent Kernel
Machine Learning @ CUED
Robust Deep Learning Under Distribution Shift
Machine Learning Reading Group @ CUED
Scalable Gaussian Processes
Machine Learning Reading Group @ CUED
Probabilistic Programming
Machine Learning Reading Group @ CUED
Neural Attention
Machine Learning Reading Group @ CUED
Equivariance and Symmetries in CNNs
Machine Learning @ CUED
Models and inference for temporal Gaussian processes
Machine Learning Reading Group @ CUED
Hyperparameter Optimisation
Machine Learning Reading Group @ CUED
Meta-Learning or "Learning To Learn"
Machine Learning @ CUED
Reinforcement Learning at Huawei: Robustness, Safety, and Efficiency
Machine Learning @ CUED
Constructing temporal latent spaces: Representation learning for clustering and imputation on time series
Machine Learning @ CUED
Explaining Neural Networks: Post-hoc and Natural Language Explanations
Machine Learning Reading Group @ CUED
Hamiltonian Monte Carlo for Hierarchical Models
Machine Learning @ CUED
Learning-Algorithms from Bayesian Principles
Machine Learning @ CUED
Rotation Invariant Householder Parameterization for Bayesian PCA
Machine Learning @ CUED
Two Approximate Sampling Methods for Bayesian Deep Learning
Machine Learning @ CUED
Semi-Unsupervised Learning with Deep Generative Models / Disentangling Improves VAEs' Robustness to Adversarial Attacks
Machine Learning @ CUED
Efficiency and Transferability of Neural Networks
Machine Learning @ CUED
Learning via Data Compression: Bayesian Coresets and Sparse Variational Inference
Machine Learning @ CUED
Deep Neural Networks: A Nonparametric Bayesian Approach with Local Competition
Machine Learning @ CUED
Information Consumption on Social Media: Efficiency, Trust, and Divisiveness
Machine Learning @ CUED
Why Do We Need New Hardware & Software for Machine Intelligence?
Machine Learning Reading Group @ CUED
Particle MCMC
Machine Learning Reading Group @ CUED
Stochastic Differential Equations
Machine Learning @ CUED
Nonparametric Generative Modeling via Optimal Transport and Diffusions with Provable Guarantees
Machine Learning Reading Group @ CUED
Generalisation in neural networks
Machine Learning Reading Group @ CUED
An Overview of Normalizing Flows
Machine Learning @ CUED
NeVAE: A Deep Generative Model for Molecular Graphs
Machine Learning @ CUED
Global model explainability via aggregation
Machine Learning Reading Group @ CUED
Sampling as Optimization
Machine Learning @ CUED
Robust machine learning for causal inference in health care
Computational Neuroscience
The K-FAC method for neural network optimization
Machine Learning Reading Group @ CUED
Implicit Variational Inference
Machine Learning Reading Group @ CUED
Continual Learning: Definitions, Benchmarks, and Approaches
Machine Learning Reading Group @ CUED
Causal Inference and Causal Reinforcement Learning
Machine Learning Reading Group @ CUED
Generative models for few-shot prediction tasks
Machine Learning @ CUED
Online Meta-Learning
Machine Learning Reading Group @ CUED
Logical Uncertainty
Computational Neuroscience
High-dimensional dynamics of generalization error in neural networks: implications for experience replay
Machine Learning @ CUED
Gauge Equivariant Convolutional Networks on Manifolds
Machine Learning Reading Group @ CUED
Stein Discrepancy
Machine Learning @ CUED
Observation and Intervention Incentives in Causal Influence Diagrams: Towards an Understanding of Powerful Machine Learning Systems
Machine Learning @ CUED
Fairness for Sequential Decision Making Algorithms
Machine Learning @ CUED
Gaussian processes for inferring latent functions in complex data models
Machine Learning Reading Group @ CUED
Neural Ordinary Differential Equations
Machine Learning Reading Group @ CUED
Natural gradient in deep neural networks
Machine Learning Reading Group @ CUED
Graph Neural Networks
Machine Learning Reading Group @ CUED
Defending Against Adversarial Attacks
Machine Learning Reading Group @ CUED
Reinforcement Learning and Control as Probabilistic Inference
Machine Learning @ CUED
Causal Inference for Treatment Effects: A Theory and Associated Learning Algorithms
Machine Learning @ CUED
Interpretability - the myth, questions, and some answers
Machine Learning @ CUED
Constraint-based causal Discovery from NOnstationary/heterogeneous Data (CD-NOD)
Machine Learning @ CUED
Fast yet Simple Natural-Gradient Variational Inference in Complex Models
Machine Learning @ CUED
Variance in Policy Gradient methods and Learning Sequential Latent Variable Models
Machine Learning @ CUED
Structured deep models: Deep learning on graphs and beyond
Machine Learning @ CUED
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
Machine Learning @ CUED
Semi-Generative Modelling: Domain Adaptation with Cause and Effect Features
Machine Learning @ CUED
Algorithmic Glass Ceiling in Social Networks
Machine Learning @ CUED
A Bayesian Perspective on Generalization and SGD
Machine Learning @ CUED
Algorithmic Glass Ceiling in Social Networks
Machine Learning Reading Group @ CUED
Neural Networks and Natural Language Processing
Machine Learning @ CUED
Structure in tensor-variate data: a trivial byproduct of simpler phenomena?
Machine Learning Reading Group @ CUED
Information Theory, Codes, and Compression
Machine Learning @ CUED
Lipschitz Global Optimization
Machine Learning Reading Group @ CUED
Statistical Learning Theory
Machine Learning Reading Group @ CUED
Deep Generative Models
Machine Learning Reading Group @ CUED
Minimum Description Length
Machine Learning Reading Group @ CUED
Machine Learning for Sounds
Machine Learning Reading Group @ CUED
NIPS 2017 Highlights
Machine Learning @ CUED
Variational inference for some models with Polya-Gamma latent variables and Gaussian process priors
Machine Learning @ CUED
Bayesian Generative Adversarial Networks
Machine Learning @ CUED
AI for Inclusive Finance
Machine Learning Reading Group @ CUED
Hardware Efficient Machine Learning
Machine Learning @ CUED
Backprop through the Void: Optimizing Control Variates for Black-Box Gradient Estimation.
Machine Learning @ CUED
Learning to Learn without Gradient Descent by Gradient Descent
Machine Learning Reading Group @ CUED
Learning to Learn
Machine Learning @ CUED
Towards true end-to-end learning & optimization
Machine Learning Reading Group @ CUED
WGAN and Optimal Transport
Machine Learning Reading Group @ CUED
Interpretability in Machine Learning
Machine Learning Reading Group @ CUED
Deep Structured Prediction for Handwriting Recognition
Machine Learning @ CUED
Targeted Disclosure to Support Auditing and Accountability for Automated Decision-making
Machine Learning Reading Group @ CUED
Cooperative Inverse RL
Machine Learning Reading Group @ CUED
Infer.NET
Machine Learning @ CUED
Nonlinear ICA using temporal structure: a principled framework for unsupervised deep learning
Machine Learning @ CUED
Transfer Learning for NLP
Machine Learning @ CUED
A Bayesian Treatment for Uncertainty -- and its application in health care
Machine Learning @ CUED
Unbiased Estimation of the Eigenvalues of Large Implicit Matrices
Machine Learning @ CUED
The Grammar Variational Autoencoder & Counterfactual Fairness
Machine Learning @ CUED
Accelerating computation of SVM and DNN by binary approximation
Machine Learning @ CUED
Towards User-Friendly Image Inpainting: Learning-to-Rank based Image Quality Assessment for Image Inpainting
Machine Learning @ CUED
Deep learning for autonomous driving
Machine Learning @ CUED
Understanding Black-box Predictions via Influence Functions
Machine Learning @ CUED
A simple neural network module for relational reasoning
Machine Learning @ CUED
Future technology: machine learning using memristors networks
Machine Learning @ CUED
Future technology: machine learning using memristors networks
Machine Learning @ CUED
On Different Distances Between Distributions and Generative Adversarial Networks
Machine Learning Study Group
Deep Learning Book - Meeting 9 - Representation Learning
Machine Learning Study Group
Deep Learning Book - Meeting 8 - Autoencoders
Machine Learning Study Group
Deep Learning Book - Meeting 7 - Neural Turing Machines & Conditional Random Fields as RNNs
Machine Learning Reading Group @ CUED
Kernel Mean Embeddings
Information Engineering Division seminar list
Bayesian Optimization for Probabilistic Programs
Machine Learning Study Group
Deep Learning Book - Meeting 6 - Recurrent Neural Networks
Machine Learning @ CUED
Differentially Private Bayesian Learning
Computational and Biological Learning Seminar Series
Control, inference and learning
Machine Learning Reading Group @ CUED
Differential Privacy
Machine Learning @ CUED
Differential Privacy Tutorial
Machine Learning Study Group
Deep Learning Book - Meeting 5 - ResNets and DenseNets
Machine Learning @ CUED
Cooperative Inverse Reinforcement Learning
Machine Learning Study Group
Deep Learning Book - Meeting 4 - Convolutional Networks
Machine Learning Reading Group @ CUED
Probabilistic Numerics
Machine Learning Study Group
Deep Learning Book - Meeting 3 - Optimization
Machine Learning @ CUED
Bayesian optimisation in many dimensions with bespoke probabilistic programs
Machine Learning Study Group
Deep Learning Book - Meeting 2 - Regularization
Machine Learning Study Group
Deep Learning Book - Meeting 1 - Deep Feedforward NNs
Machine Learning @ CUED
Variational Bayes In Private Settings
Machine Learning @ CUED
Julia: Introduction and new developments
Machine Learning Reading Group @ CUED
NIPS 2016 papers in 5mins
Machine Learning @ CUED
Bayesian optimality and frequentist extended admissibility are equivalent in saturated models
Machine Learning @ CUED
Hierarchical Multi-Agent Reinforcement Learning through Communicative Actions for Human-Robot Collaboration
Machine Learning @ CUED
Variational autoencoders with latent graphical models
Machine Learning Reading Group @ CUED
Symmetry in Statistical Models
Machine Learning @ CUED
Learning with limited supervision
Machine Learning Reading Group @ CUED
Bayesian Optimization
Machine Learning @ CUED
A tale of P-matrices and TripleSpinners - the unreasonable effectiveness of structured models in nonlinear embeddings
Machine Learning @ CUED
Rejection Sampling Variational Inference
Machine Learning Reading Group @ CUED
deep generative models
Machine Learning @ CUED
Probabilistic Numerical Computation: A New Concept?
Machine Learning Reading Group @ CUED
Sketching methods
Machine Learning @ CUED
A talk in two parts: (1) AI Neuroscience: How much do deep neural networks understand about the images they classify? (2) Robots that can adapt like animals.
β οΈ Note venue: James Dyson Building
Machine Learning Reading Group @ CUED
A crash-course on Bayesian Reinforcement Learning
Machine Learning @ CUED
Multi-view Anomaly Detection via Robust Probabilistic Latent Variable Models
Machine Learning @ CUED
Robots learning on the move: deep learning from lots of demonstration
Machine Learning @ CUED
Probabilistic modeling for position and orientation estimation using inertial sensors
Machine Learning @ CUED
Moment matching for latent variable models: from ICA to LDA and CCA
Machine Learning @ CUED
Multiresolution Matrix Factorization
Machine Learning @ CUED
Dynamic Models for Health Data
Machine Learning @ CUED
Learning with Memory Embeddings
Machine Learning @ CUED
Data Driven Discrete Time Modeling of Continuous Time Nonlinear Systems: Problems, Challenges, Success Stories
Machine Learning @ CUED
Inference as Learning
Machine Learning @ CUED
Interpretable and interactive machine learning
Machine Learning @ CUED
Discriminative Embeddings of Latent Variable Models for Structured Data
Machine Learning @ CUED
Structured Dynamic Graphical Models & Scaling Multivariate Time Series Methodology
Machine Learning @ CUED
Scaling and Generalizing Approximate Bayesian Inference
arg58's list
A modular architecture for Unicode text compression
Machine Learning @ CUED
Modeling the Dynamics of Online Learning Activity
Machine Learning @ CUED
Developments in Exact Inference in Graphical Models
Machine Learning @ CUED
Approximation strategies for structure learning in Bayesian networks
β οΈ Note: via Skype!
Machine Learning @ CUED
Automated Reasoning and AI for Large Formal Mathematics
Machine Learning Reading Group @ CUED
Partially Observable Markov Decision Processes (POMDPs)
Machine Learning @ CUED
Variational inference for scalable Gaussian process approximations
Machine Learning @ CUED
Novel MCMC and SMC schemes for Poisson-Kingman Bayesian Nonparametric mixture models
Machine Learning @ CUED
Turing: Rejuvenating Probabilistic Programming in Julia
Machine Learning @ CUED
Towards Weaker Supervision and Simpler Pipelines in Speech Recognition
Machine Learning Reading Group @ CUED
Learning polynomials with Neural Networks
Machine Learning @ CUED
Sum-Product Networks for Probabilistic Modeling
Machine Learning @ CUED
MLE-Struct: Bethe Learning of Graphical Models
Machine Learning Reading Group @ CUED
An introduction to Bayesian nonparametrics: some inference schemes for infinite mixture models
Machine Learning Reading Group @ CUED
Topics in Expectation Propagation
Machine Learning Reading Group @ CUED
Deep Q-Learning and AlphaGo
Machine Learning Reading Group @ CUED
inference failures in probabilistic programming
Machine Learning Reading Group @ CUED
Variational Methods and Compressed Sensing
Machine Learning @ CUED
Inference and Learning in the Anglican Probabilistic Programming System
Machine Learning Reading Group @ CUED
Fast Fusion of Multi-band Images: A Powerful Tool for Super-resolution
Machine Learning @ CUED
Unsupervised Risk Estimation with only Structural Assumptions
Computational Neuroscience
It's the Network Dummy: Exhuming the reticular theory while shoveling a little dirt on the neuron doctrine
Machine Learning @ CUED
The geometry of uncertainty
Machine Learning Reading Group @ CUED
Probabilistic programming
Machine Learning Reading Group @ CUED
Learning by learning rich generative models
Machine Learning @ CUED
A more Automated Statistician
Machine Learning Reading Group @ CUED
Natural gradient descent and variational inference
Machine Learning Reading Group @ CUED
Differentiable Data Structures and (if we have time) POMDPs
β οΈ NOTE Topic Change
Machine Learning Reading Group @ CUED
Random projection ensemble classification
Machine Learning Reading Group @ CUED
Deep learning for time series
Machine Learning Reading Group @ CUED
Stochastic discrete integration
Machine Learning @ CUED
General Reinforcement Learning
Machine Learning Reading Group @ CUED
Stochastic optimization and adaptive learning rates
Machine Learning Reading Group @ CUED
Logic, Theorem Proving, and Probabilistic Programming
Machine Learning Reading Group @ CUED
Connections between kernels, GPs, and NNs
Machine Learning @ CUED
Inference of a partially observed kinetic Ising model
Machine Learning Reading Group @ CUED
Detecting paraphrases using recursive autoencoders
Machine Learning Reading Group @ CUED
Bayesian optimization and its applications
Machine Learning Reading Group @ CUED
LP relaxations for MAP inference
Machine Learning @ CUED
Meta-Bayesian Analysis
Machine Learning @ CUED
Efficient Inference and Learning with Intractable Posteriors? Yes, Please.
Machine Learning @ CUED
Efficient multi-task Gaussian process models for genome-wide association studies
Machine Learning @ CUED
Harmonic Exponential Families and Group-Equivariant Convolution Networks
Machine Learning @ CUED
Higher Order Fused Regularization for Supervised Learning with Grouped Parameters
Machine Learning @ CUED
A-Star Sampling Review
Machine Learning @ CUED
Convex Factorization Machines
Machine Learning @ CUED
Belief and Truth in Hypothesised Behaviours
Machine Learning @ CUED
Training and Understanding Deep Neural Networks for Robotics, Design, and Perception
Machine Learning @ CUED
Information-Theoretic Bounded Rationality
Machine Learning @ CUED
The limits of MAP inference by MWSS on perfect graphs
Machine Learning @ CUED
Scalable Gaussian Processes for Scientific Discovery
Machine Learning @ CUED
MCMC for non-linear state space models using ensembles of latent sequences
β οΈ (via Skype!)
Machine Learning @ CUED
Gradient-based hyperparameter optimization through reversible learning
Machine Learning @ CUED
Rich Component Analysis
Machine Learning @ CUED
A new MCMC hybrid scheme for Poisson-Kingman Bayesian Nonparametric mixture models
Machine Learning @ CUED
Modeling Confounding by Half-Sibling Regression
β οΈ SHORT TALK (20 minutes)
Machine Learning @ CUED
Extreme Classification: A New Paradigm for Ranking & Recommendation
Machine Learning @ CUED
Convex and non-convex worlds in machine learning
Machine Learning @ CUED
Random Function Classes for Machine Learning
Machine Learning @ CUED
Explaining Non-Linear Classifier Decisions with application to Deep Learning
Machine Learning @ CUED
Deep Gaussian processes and variational propagation of uncertainty
Machine Learning @ CUED
Deep Learning
Machine Learning @ CUED
Random Function Classes for Machine Learning
Machine Learning @ CUED
Unsupervised Learning with Latent Variable Models
Machine Learning @ CUED
Unsupervised Learning with Latent Variable Models
Machine Learning @ CUED
Structural Markov laws / Geometry and HMC
Machine Learning @ CUED
Mean Field Approaches to Two Sequential Decision Making Problems.
β οΈ This talk will be given via Skype
Machine Learning @ CUED
Do Deep Nets Really Need to be Deep?
Machine Learning Reading Group @ CUED
Convolutional Neural Networks
Machine Learning Reading Group @ CUED
Hessian-free Optimisation for Neural Networks
Machine Learning @ CUED
Probabilistic numerics: treating numerical computation as learning, or; it's Bayes all the way down
Machine Learning Reading Group @ CUED
Scalable MCMC
Machine Learning @ CUED
Machine Learning for Quantitative Finance: A collaboration between the Cambridge Machine Learning Group and Cambridge Capital Management
Machine Learning Reading Group @ CUED
Causal Inference
Machine Learning @ CUED
Title to be confirmed
Machine Learning Reading Group @ CUED
Gaussian Process Models for Time Series
Machine Learning @ CUED
Inference for infinite mixture models and Gaussian Process mixtures of experts using simple approximate MAP Inference
Machine Learning Reading Group @ CUED
Informational Geometry
Machine Learning Reading Group @ CUED
Deep Gaussian Processes
Machine Learning Reading Group @ CUED
Combinatorial Stochastic Processes in Bayesian Nonparametrics
Machine Learning @ CUED
Evolutionary dynamics in a continuous public goods game
Machine Learning @ CUED
An introduction to the Mondrian Process
Machine Learning @ CUED
Population Inference for Functional Brain Connectivity
Microsoft Research Machine Learning and Perception Seminars
Workshop: Machine Learning in Cambridge 2015
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Machine Learning @ CUED
Probabilistic approaches to understanding bird conversations
Machine Learning @ CUED
A* Sampling
Machine Learning Reading Group @ CUED
Variance Reduction Techniques and Stochastic Optimisation for Monte Carlo
Machine Learning @ CUED
Orthologous networks in biological systems
Machine Learning Reading Group @ CUED
Transfer Learning
Machine Learning @ CUED
Latent Branching Trees
Machine Learning @ CUED
Experiments with Non-parametric Topic Models
Machine Learning Reading Group @ CUED
Advanced HMC
Machine Learning Reading Group @ CUED
Active Learning
Machine Learning @ CUED
The Blended Paradigm: A Bayesian Approach to Handling Outliers and Misspecified Models
Machine Learning Reading Group @ CUED
Deep Probabilistic Models (Wake/Sleep)
Machine Learning @ CUED
Machine Translation with LSTMs
β οΈ Room changed to LR3B in Inglis building and time changed to 10:30
Machine Learning Reading Group @ CUED
PAC Bayes
Machine Learning @ CUED
Oracle Variational Inference
Machine Learning Reading Group @ CUED
LSTM and Recurrent Neural Networks
Machine Learning @ CUED
Bayesian modeling for high-level real nursing activity recognition using accelerometers
β οΈ short talk
Machine Learning Reading Group @ CUED
Automatic Differentiation with Theano
Machine Learning Reading Group @ CUED
State Space Abstraction for Reinforcement Learning
Machine Learning Reading Group @ CUED
Kernel Embedding for Distributions
Machine Learning @ CUED
A Tutorial on Probabilistic Programming
CUED Control Group Seminars
Optimal control and optimal sampling: A statistical physics perspective.
Machine Learning @ CUED
New Methods in Bayesian Optimization for Machine Learning
Machine Learning @ CUED
A marginal sampler for Ο-Stable Poisson-Kingman mixture models
Machine Learning @ CUED
Local Deep Kernel Learning for Efficient Non-linear SVM Prediction
Microsoft Research Machine Learning and Perception Seminars
Local Deep Kernel Learning for Efficient Non-linear SVM Prediction
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Machine Learning @ CUED
Unsupervised Many-to-many Object Matching
Machine Learning @ CUED
Probabilistic Numerics - a snapshot of an emerging community
Machine Learning @ CUED
On the Bethe approximation
Machine Learning @ CUED
Gaussian process regression on graphs
Machine Learning @ CUED
Implicit Representation Networks
Machine Learning @ CUED
Scalable Deep Gaussian Processes
Machine Learning Reading Group @ CUED
Unsupervised Representation Learning
Machine Learning @ CUED
Active Learning of Linear Embeddings for Gaussian Processes
Machine Learning @ CUED
Bayesian monitoring for the Comprehensive Nuclear-Test-Ban Treaty
Machine Learning @ CUED
Unifying logic and probability: A "New Dawn" for Artificial Intelligence?
β οΈ NOTE THE SPECIAL VENUE (Microsoft Research)
Machine Learning Reading Group @ CUED
ββTime-varying dynamic Bayesian network reconstruction with information sharingβ
Machine Learning Reading Group @ CUED
Advanced Gaussian Process approximation methods
Machine Learning @ CUED
Practical Machine Learning at Facebook. Examples and Lessons Learnt.
β οΈ Room changed to LR4
Machine Learning @ CUED
Bayesian inference for integer-valued LΓ©vy processes with Non-Gaussian Ornstein-Uhlenbeck volatility modelling
β οΈ short talk (30 mins) - NOTE TIME CHANGE
Machine Learning Reading Group @ CUED
Statistical model criticism
Machine Learning @ CUED
Density Estimation in Infinite Dimensional Exponential Families
Machine Learning @ CUED
Stable Poisson-Kingman species sampling priors generated by general ordered size biased generalized gamma mixing distributions
Machine Learning Reading Group @ CUED
Functional Programming
Machine Learning Reading Group @ CUED
The Bernoulli Factory problem and some connections with Computable Analysis
Machine Learning Reading Group @ CUED
Neural Network Language Modelling
Machine Learning @ CUED
Probabilistic computing applications: BayesDB and stochastic digital circuits
Machine Learning Reading Group @ CUED
Loopy belief propagation
Machine Learning @ CUED
Probabilistic computing for Bayesian inference
Machine Learning @ CUED
Machine Learning and Order Book Dynamics
Machine Learning @ CUED
Policy Evaluation with Temporal Differences
Machine Learning @ CUED
Matrix Means, Distances, Kernels, and Geometric Optimization
Machine Learning @ CUED
Learning to Learn for Structured Sparsity
Machine Learning @ CUED
Bayesian nonparametric dynamic-clustering and genetic imputation
Machine Learning @ CUED
Parameter estimation in deep learning architectures: Two new insights.
β οΈ Note: time is 12 noon (*not* 11am)
Machine Learning @ CUED
Bayesian canonical correlation analysis
Machine Learning @ CUED
Cambridge - Tuebingen PhD Applicant Talks (via Skype)
β οΈ Interview talks via Skype
Machine Learning @ CUED
Generative probabilistic programming: applications and new ideas
Machine Learning @ CUED
Bayesian nonparametrics: Dependency and Constraint Modeling
β οΈ Note: TALK via Skype!
Machine Learning @ CUED
Bayesian Nonparametric Model for Power Disaggregation
Machine Learning @ CUED
Probabilistic machine learning for knowledge extraction from videos and text
β οΈ Note venue: LR6
Machine Learning Reading Group @ CUED
An introduction to Sequential Monte Carlo
Machine Learning @ CUED
Frequentist coverage of adaptive nonparametric Bayesian credible sets
Machine Learning Reading Group @ CUED
Probabilistic Data Structures and Algorithms
Machine Learning Reading Group @ CUED
Information Theory and Method of Types: Channels, Quantizers, and Divergences
Machine Learning @ CUED
Anglican; Particle MCMC inference for Probabilistic Programs
Machine Learning @ CUED
Sparse discriminative latent characteristics for predicting cancer drug sensitivity
Microsoft Research Machine Learning and Perception Seminars
Bayesian Machine Learning for Controlling Autonomous Systems
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Machine Learning Reading Group @ CUED
Integrated Nested Laplace Approximation (INLA)
Machine Learning Reading Group @ CUED
Spectral Learning
Machine Learning Reading Group @ CUED
Random Projections
Machine Learning @ CUED
Contrastive Learning Using Spectral Methods
Machine Learning Reading Group @ CUED
Herding: Driving Deterministic Dynamics To Learn And Sample Probabilistic Models
Machine Learning Reading Group @ CUED
Bayesian and Bandit Optimization
Machine Learning @ CUED
Nonparametric Bayesian statistics with exchangeable random structures
Machine Learning @ CUED
Dissecting genotype to phenotype relationships
Microsoft Research Machine Learning and Perception Seminars
Compositionality in Vision and Language
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Machine Learning @ CUED
CANCELLED: Local Deep Kernel Learning for Efficient Non-linear SVM Prediction
β οΈ CANCELLED
Machine Learning @ CUED
Clustering Based on Predictive Variances in Gaussian Process Regression Models
Microsoft Research Machine Learning and Perception Seminars
Foundations of Neuromechanical Systems Biology: Combining engineering, biology, and mathematics to understand how we move
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Microsoft Research Machine Learning and Perception Seminars
Strategies for General Recognition
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Microsoft Research Machine Learning and Perception Seminars
The cost of principles
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Machine Learning @ CUED
Non-Parametric Conditional Random Fields in Computer Vision and Image Processing
Machine Learning @ CUED
Higher Order Learning for Classification in Emergency Situations
Microsoft Research Machine Learning and Perception Seminars
Lifts of Convex Sets and Cone Factorizations
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Machine Learning @ CUED
Annealing Between Distributions by Averaging Moments
Microsoft Research Machine Learning and Perception Seminars
Efficient Multi-dimensional Parametric Mincuts for Constrained MAP Inference
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
NLIP Seminar Series
Recursive Deep Learning for Modeling Semantic Compositionality
Microsoft Research Machine Learning and Perception Seminars
Noise estimation by PDE-constrained optimisation
β οΈ This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Machine Learning Reading Group @ CUED
Random Forests: One tool for all your problems.
Machine Learning @ CUED
Applied statistical genetics and next-generation association studies
Machine Learning @ CUED
Applied statistical genetics and next-generation association studies
Machine Learning Reading Group @ CUED
Modelling Nonlinear Dynamical Systems
Machine Learning @ CUED
The combinatorial structure of conditionally i.i.d. negative binomial processes directed by a beta process
Please see above for contact details for this list.