7 papers
Inference and learning in sparse autoencoders as natural gradient flow
Hadi Vafaii, Tejas Rao, David Chanin +6
Sparse autoencoders are widely used to uncover interpretable features in neural networks, yet reliable recovery remains difficult when features overlap or activate infrequently. Th…
Metabolic cost of information processing in Poisson variational autoencoders
Hadi Vafaii, Jacob L. Yates
Computation in biological systems is fundamentally energy-constrained, yet standard theories of computation treat energy as freely available. Here, we argue that variational free e…
A hitchhiker's guide to Poisson gradient estimation
Michael Ibrahim, Hanqi Zhao, Eli Sennesh +5
Poisson-distributed latent variable models are widely used in computational neuroscience, but differentiating through discrete stochastic samples remains challenging. Two approache…
Inferring response times of perceptual decisions with Poisson variational autoencoders
Hayden R. Johnson, Anastasia N. Krouglova, Hadi Vafaii +2
Many properties of perceptual decision making are well-modeled by deep neural networks. However, such architectures typically treat decisions as instantaneous readouts, overlooking…
Unveiling Secrets of Brain Function With Generative Modeling: Motion Perception in Primates & Cortical Network Organization in Mice
Hadi Vafaii
This Dissertation is comprised of two main projects, addressing questions in neuroscience through applications of generative modeling. Project #1 (Chapter 4) explores how neurons e…
Brain-like Variational Inference
Hadi Vafaii, Dekel Galor, Jacob L. Yates
Inference in both brains and machines can be formalized by optimizing a shared objective: maximizing the evidence lower bound (ELBO) in machine learning, or minimizing variational…
Poisson Variational Autoencoder
Hadi Vafaii, Dekel Galor, Jacob L. Yates
Variational autoencoders (VAEs) employ Bayesian inference to interpret sensory inputs, mirroring processes that occur in primate vision across both ventral (Higgins et al., 2021) a…