2 citations · 4 across the 7 of their papers we have counts for
6 papers · 1 filter
Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescaling
Sanjith Senthil, Rishidev Chaudhuri
The pruning of network connections is key to brain function but, despite its importance, there exist few biologically-plausible pruning rules with demonstrated good performance. In…
Harnessing and modulating chaos to sample from neural generative models
Rishidev Chaudhuri, Vivek Handebagh
Chaos is generic in strongly-coupled recurrent networks of model neurons, and thought to be an easily accessible dynamical regime in the brain. While neural chaos is typically seen…
Adaptive Synaptic Failure Enables Sampling from Posterior Predictive Distributions in the Brain
Kevin McKee, Ian Crandell, Rishidev Chaudhuri +1
Bayesian interpretations of neural processing require that biological mechanisms represent and operate upon probability distributions in accordance with Bayes' theorem. Many have s…
Locally Learned Synaptic Dropout for Complete Bayesian Inference
Kevin L. McKee, Ian C. Crandell, Rishidev Chaudhuri +1
The Bayesian brain hypothesis postulates that the brain accurately operates on statistical distributions according to Bayes' theorem. The random failure of presynaptic vesicles to…
Using noise to probe recurrent neural network structure and prune synapses
Eli Moore, Rishidev Chaudhuri
Many networks in the brain are sparsely connected, and the brain eliminates synapses during development and learning. How could the brain decide which synapses to prune? In a recur…
Associative content-addressable networks with exponentially many robust stable states
Rishidev Chaudhuri, Ila Fiete
The brain must robustly store a large number of memories, corresponding to the many events encountered over a lifetime. However, the number of memory states in existing neural netw…