![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
![]() Multitask LearningAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact David Greaves. Machine learning studies the problem of learning to perform a given task from a dataset of examples. A fundamental limitation of standard machine learning methods is the cost incurred in preparing large training datasets. Often in applications a limited number of examples is available and the task cannot be solved in isolation. A potential remedy is offered by multitask learning, which aims to learn several related tasks simultaneously. If the tasks share some constraining or generative property which is sufficiently simple it should allow for better learning of the individual tasks even when the individual training datasets are small. In the talk, I will present a wide class of multitask learning methods which encourage different forms of task relatedness and involve certain notions of structured sparsity and low rank tensor representations. I will also discuss iterative algorithms to implement these methods, building upon ideas from convex optimisation. Finally, I will illustrate the performance of these methods in applications arising in affective computing, computer vision and user modelling. This talk is part of the Computer Laboratory Wednesday Seminars series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsGlobal Sustainability Institute Seminars & Events Centre for Commonwealth Education (CCE) Finance and Accounting Subject Group Microelectronics Group Seminar middle east studies MathematicsOther talksProtein Folding, Evolution and Interactions Symposium The Galactic Centre: a template for understanding star formation and feedback in a high-pressure environment The role of Birkeland currents in the Dungey cycle Organic Bio-Electronic systems: from tissue engineering to drug discovery Atmospheric Retrieval CANCELLED First year PhD student fieldwork seminar EU LIFE Lecture - "Histone Chaperones Maintain Cell Fates and Antagonize Reprogramming in C. elegans and Human Cells" Protein Folding, Evolution and Interactions Symposium Immigration and Freedom Computing knot Floer homology Formation and disease relevance of axonal endoplasmic reticulum, a "neuron within a neuron”. Social Representations of Women who Live as Men in Northern Albania |