paper-with-me

홈 › Papers

Using noise to probe recurrent neural network structure and prune synapses

2020-11-14 · NeurIPS 2020 12 · 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 recurrent network, determining the importance of a synapse between two neurons is a difficult computational problem, depending on the role that both neurons play and on all possible pathways of information flow between them. Noise is ubiquitous in neural systems, and often considered an irritant to be overcome. Here we suggest that noise could play a functional role in synaptic pruning, allowing the brain to probe network structure and determine which synapses are redundant. We construct a simple, local, unsupervised plasticity rule that either strengthens or prunes synapses using only synaptic weight and the noise-driven covariance of the neighboring neurons. For a subset of linear and rectified-linear networks, we prove that this rule preserves the spectrum of the original matrix and hence preserves network dynamics even when the fraction of pruned synapses asymptotically approaches 1. The plasticity rule is biologically-plausible and may suggest a new role for noise in neural computation.

📄 PDF Abstract BibTeX arXiv:2011.07334

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Self-building Neural Networks

2023-04-03 · Andrea Ferigo, Giovanni Iacca

During the first part of life, the brain develops while it learns through a process called synaptogenesis. The neurons, growing and interacting with each other, create synapses. However, eventually the brain prunes those…

STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition

2017-10-12 · Nitin Rathi, Priyadarshini Panda, Kaushik Roy

Spiking Neural Networks (SNNs) with a large number of weights and varied weight distribution can be difficult to implement in emerging in-memory computing hardware due to the limitations on crossbar size (implementing do…

General ClassificationQuantization

Examining and Mitigating the Impact of Crossbar Non-idealities for Accurate Implementation of Sparse Deep Neural Networks

2022-01-13 · Abhiroop Bhattacharjee, Lakshya Bhatnagar, Priyadarshini Panda

Recently several structured pruning techniques have been introduced for energy-efficient implementation of Deep Neural Networks (DNNs) with lesser number of crossbars. Although, these techniques have claimed to preserve …

Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN

2024-03-06 · Biswadeep Chakraborty, Beomseok Kang, Harshit Kumar, Saibal Mukhopadhyay

Recurrent Spiking Neural Networks (RSNNs) have emerged as a computationally efficient and brain-inspired learning model. The design of sparse RSNNs with fewer neurons and synapses helps reduce the computational complexit…

Computational EfficiencyDiversityimage-classificationImage Classification

Synaptic balancing: a biologically plausible local learning rule that provably increases neural network noise robustness without sacrificing task performance

2021-07-18 · Christopher H. Stock, Sarah E. Harvey, Samuel A. Ocko, Surya Ganguli

We introduce a novel, biologically plausible local learning rule that provably increases the robustness of neural dynamics to noise in nonlinear recurrent neural networks with homogeneous nonlinearities. Our learning rul…