Search Results for author:
Found 5 papers, 2 papers with code
Growing Brains: Co-emergence of Anatomical and Functional Modularity in Recurrent Neural Networks
Recurrent neural networks (RNNs) trained on compositional tasks can exhibit functional modularity, in which neurons can be clustered by activity similarity and participation in shared computational subtasks.
Noisy dynamical systems evolve error correcting codes and modularity
Noise is a ubiquitous feature of the physical world.
Fault-Tolerant Neural Networks from Biological Error Correction Codes
It has been an open question in deep learning if fault-tolerant computation is possible: can arbitrarily reliable computation be achieved using only unreliable neurons?
Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold
We propose a novel CAM architecture, Memory Scaffold with Heteroassociation (MESH), that factorizes the problems of internal attractor dynamics and association with external content to generate a CAM continuum without a memory cliff: Small numbers of patterns are stored with complete information recovery matching standard CAMs, while inserting more patterns still results in partial recall of every pattern, with a graceful trade-off between pattern number and pattern richness.
Attractor and integrator networks in the brain
In this review, we describe the singular success of attractor neural network models in describing how the brain maintains persistent activity states for working memory, error-corrects, and integrates noisy cues.
