3 papers
cs.LG2024
A Unified Theory of Exact Inference and Learning in Exponential Family Latent Variable Models
Sacha Sokoloski
Bayes' rule describes how to infer posterior beliefs about latent variables given observations, and inference is a critical step in learning algorithms for latent variable models (…
cs.NE2024
A computational approach to visual ecology with deep reinforcement learning
Sacha Sokoloski, Jure Majnik, Philipp Berens
Animal vision is thought to optimize various objectives from metabolic efficiency to discrimination performance, yet its ultimate objective is to facilitate the survival of the ani…
cs.NE2012
A Biologically Realistic Model of Saccadic Eye Control with Probabilistic Population Codes
Sacha Sokoloski
The posterior parietal cortex is believed to direct eye movements, especially in regards to target tracking tasks, and a number of debates exist over the precise nature of the comp…