Abstract Simple Gaussian Mixture Models (GMMs) learned from pixels of natural image
patches have been recently shown to be surprisingly strong performers in modeling the …

Predictive state representations (PSRs) offer an expressive framework for modelling partially
observable systems. By compactly representing systems as functions of observable …

The efficient coding hypothesis holds that neural receptive fields are adapted to the statistics
of the environment, but is agnostic to the timescale of this adaptation, which occurs on both …

We study inference and learning based on a sparse coding model with 'spike-and-slab'prior.
As in standard sparse coding, the model used assumes independent latent sources that …

A convolutional factor-analysis model is developed, with the number of filters (factors)
inferred via the beta process (BP) and hierarchical BP, for single-task and multi-task …

Latent variable models (LVMs) represent observed variables by parameterized functions of
latent variables. Prominent examples of LVMs for unsupervised learning are probabilistic …

The sparse coding hypothesis has enjoyed much success in predicting response properties
of simple cells in primary visual cortex (V1) based solely on the statistics of natural scenes …

Independent component and canonical correlation analysis are two general-purpose
statistical methods with wide applicability. In neuroscience, independent component …

We investigate how the neural processing in auditory cortex is shaped by the statistics of
natural sounds. Hypothesising that auditory cortex (A1) represents the structural primitives …

We study the task of cleaning scanned text documents that are strongly corrupted by dirt
such as manual line strokes, spilled ink, etc. We aim at autonomously removing such …