Special year seminar - Math

There are three core orthogonal problems in reinforcement learning: (1) Crediting actions (2) generalizing across rich observations (3) Exploring to discover the information necessary for learning. Good solutions to pairs of these problems are fairly well known at this point, but solutions for...

Probably Approximately Correct (PAC) learning has attempted to analyse the generalisation of learning systems within the statistical learning framework. It has been referred to as a ‘worst case’ analysis, but the tools have been extended to analyse cases where benign distributions mean we can...

In handling wide range of experiences ranging from data instances, knowledge, constraints, to rewards, adversaries, and lifelong interplay in an ever-growing spectrum of tasks, contemporary ML/AI research has resulted in thousands of models, learning paradigms, optimization algorithms, not...

Unsupervised learning, in particular learning general nonlinear representations, is one of the deepest problems in machine learning. Estimating latent quantities in a generative model provides a principled framework, and has been successfully used in the linear case, e.g. with independent...

For autonomous robots to operate in the open, dynamically changing world, they will need to be able to learn a robust set of skills from relatively little experience. This talk begins by introducing Grounded Simulation Learning as a way to bridge the so-called reality gap between simulators and...

I will introduce Generalized Energy Based Models (GEBM) for generative modelling. These models combine two trained components: a base distribution (generally an implicit model), which can learn the support of data with low intrinsic dimension in a high dimensional...