
Neural Density Estimation and Likelihoodfree Inference
I consider two problems in machine learning and statistics: the problem ...
read it

Normative theory of visual receptive fields
This article gives an overview of a normative computational theory of vi...
read it

Learning EnergyBased Approximate Inference Networks for Structured Applications in NLP
Structured prediction in natural language processing (NLP) has a long hi...
read it

Applications of the Free Energy Principle to Machine Learning and Neuroscience
In this PhD thesis, we explore and apply methods inspired by the free en...
read it

Adversarial Variational Inference and Learning in Markov Random Fields
Markov random fields (MRFs) find applications in a variety of machine le...
read it

FRAME Revisited: An Interpretation View Based on Particle Evolution
FRAME (Filters, Random fields, And Maximum Entropy) is an energybased d...
read it

Approximate HubelWiesel Modules and the Data Structures of Neural Computation
This paper describes a framework for modeling the interface between perc...
read it
Contrastive Topographic Models: Energybased density models applied to the understanding of sensory coding and cortical topography
We address the problem of building theoretical models that help elucidate the function of the visual brain at computational/algorithmic and structural/mechanistic levels. We seek to understand how the receptive fields and topographic maps found in visual cortical areas relate to underlying computational desiderata. We view the development of sensory systems from the popular perspective of probability density estimation; this is motivated by the notion that an effective internal representational scheme is likely to reflect the statistical structure of the environment in which an organism lives. We apply biologically based constraints on elements of the model. The thesis begins by surveying the relevant literature from the fields of neurobiology, theoretical neuroscience, and machine learning. After this review we present our main theoretical and algorithmic developments: we propose a class of probabilistic models, which we refer to as "energybased models", and show equivalences between this framework and various other types of probabilistic model such as Markov random fields and factor graphs; we also develop and discuss approximate algorithms for performing maximum likelihood learning and inference in our energy based models. The rest of the thesis is then concerned with exploring specific instantiations of such models. By performing constrained optimisation of model parameters to maximise the likelihood of appropriate, naturalistic datasets we are able to qualitatively reproduce many of the receptive field and map properties found in vivo, whilst simultaneously learning about statistical regularities in the data.
READ FULL TEXT
Comments
There are no comments yet.