Diffusion models have gained traction as powerful algorithms for synthesizing high-quality images. Central to these algorithms is the diffusion process, a set of equations which maps data to noise in a way that can significantly affect performance. In this paper, we explore whether the diffusion process can be learned from data.

34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada

Tostudy thishypothesis, wepropose GatedL0 Regularized Dynamics (GateL0RD), a novel recurrent architecture that incorporates the inductive bias to maintain stable, sparsely changing latent states.

Recent technological advances in systems neuroscience have led to a shift away from using simple tasks with low-dimensional, well-controlled stimuli towards trying to understand neural activity during naturalistic behavior.