![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > The Pervasive Role of Composing Transformations in Machine Learning
![]() The Pervasive Role of Composing Transformations in Machine LearningAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact nobody. OGGW05 - Geometric and combinatorial methods in the foundations of computer science and artificial intelligence From the layer maps of neural networks to training procedures and reinforcement learning, compositions of transformations permeate modern AI. These compositional products often involve randomly selected maps, as in weight initialization, stochastic gradient descent (SGD), and dropout. In reinforcement learning, Bellman-type operators with randomness are iterated to update reward structures and strategies. I will discuss the mathematics and geometry underlying the composition of random transformations. In particular, I will explain a general limit law established in joint work with Gouëzel. Moreover, I will discuss a possible cut-off phenomenon related to the depth of neural networks and the influence of iteration order. Motivated by these observations, and in collaboration with Avelin, Dherin, Gonzalvo, Mazzawi, and Munn, we propose backward variants of SGD that improve stability and convergence while maintaining generalisation. This talk is part of the Isaac Newton Institute Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsRoyal Aeronautical Society (RAeS) Cambridge Branch Quiet Please! The Engineering Challenges of Detecting Gravitational Waves from Space Talks related to sustainability and the environmentOther talksSeminars in Cancer The primary role of jets in exploding all core-collapse supernovae Title TBC Keynote: Judging uncertainty from black-box classifiers Sir Partha Dasgupta – “The Price for Everything, the Value of Nothing” Thermodynamics of Disperse Polymer Blends and Solutions OR Theoretical/Computational Prediction of Polymer Mechanics |