no code implementations • 30 Apr 2024 • Sacha Sokoloski
In this paper we study the line that separates LVMs that rely on approximation schemes from those that do not, and develop a general theory of exponential family, latent variable models for which inference and learning may be implemented exactly.
no code implementations • 7 Feb 2024 • Sacha Sokoloski, Jure Majnik, Philipp Berens
To study how environments shape and constrain visual processing, we developed a deep reinforcement learning framework in which an agent moves through a 3-d environment that it perceives through a vision model, where its only goal is to survive.
no code implementations • 10 Jun 2022 • Sacha Sokoloski, Philipp Berens
Here, we show how a family of such two-stage models can be combined into a single, hierarchical model that we call a hierarchical mixture of Gaussians (HMoG).
no code implementations • 1 Aug 2019 • Sacha Sokoloski, Ruben Coen-Cagli
Parallel recordings of neural spike counts have revealed the existence of context-dependent noise correlations in neural populations.
no code implementations • 22 Dec 2015 • Sacha Sokoloski
In order to interact intelligently with objects in the world, animals must first transform neural population responses into estimates of the dynamic, unknown stimuli which caused them.