Plasticity Rule

Plasticity, a neural network's ability to adapt to new information, is a crucial area of research in machine learning and neuroscience. Current research focuses on understanding and mitigating "plasticity loss," the phenomenon where networks become less adaptable over time, particularly in continual learning scenarios. This involves exploring various model architectures, including spiking neural networks and those incorporating biologically-inspired plasticity rules like Hebbian learning, and developing algorithms to maintain plasticity while preserving previously learned knowledge. Addressing plasticity loss is vital for creating more robust and adaptable AI systems and for gaining a deeper understanding of biological learning mechanisms.

Papers

November 7, 2024

Plasticity Loss in Deep Reinforcement Learning: A Survey
Timo Klein, Lukas Miklautz, Kevin Sidak, Claudia Plant, Sebastian Tschiatschek
Deep Learning Timely Survey Deep Reinforcement Learning Plasticity Rule Plasticity Loss

October 30, 2024

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
Baekrok Shin, Junsoo Oh, Hanseul Cho, Chulhee Yun
Neural Network Interest Loss Plasticity Rule Warm Start Stationary Distribution Plasticity Loss Practical Deep

October 26, 2024

Self-Normalized Resets for Plasticity in Continual Learning
Vivek F. Farias, Adam D. Jozefiak
Neural Network Continual LEArning Continual Learning Plasticity Rule Global Reset Feature Plasticity Loss Based Reset

October 21, 2024

Gradient-Free Supervised Learning using Spike-Timing-Dependent Plasticity for Image Recognition
Wei Xie
Neural Network LeArning Abstract Supervised Learning Back Propagation Image Recognition Plasticity Rule Gradient Free Spike Timing Dependent Plasticity

September 25, 2024

Neural Network Plasticity and Loss Sharpness
Max Koster, Jude Kukla
Continual LEArning Plasticity Rule Synaptic Plasticity Plasticity Loss

August 28, 2024

Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing
Kenneth Stewart, Michael Neumeier, Sumit Bam Shrestha, Garrick Orchard, Emre Neftci
Neuromorphic Computing Neuromorphic Hardware Plasticity Rule Brain Inspired Local Plasticity

July 27, 2024

June 14, 2024

Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning
Erwan Plantec, Joachin W. Pedersen, Milton L. Montero, Eleni Nisioti, Sebastian Risi
Neural Network Plasticity Rule Neural Program Spontaneous Motor Experience Driven Reinforcement Learning

June 7, 2024

Unsupervised representation learning with Hebbian synaptic and structural plasticity in brain-like feedforward neural networks
Naresh Ravichandran, Anders Lansner, Pawel Herman
Neural Network Unsupervised Representation Learning Plasticity Rule Brain Inspired Associative Memory Feed Forward Layer Hebbian Plasticity Brain Computation

June 1, 2024

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
Hojoon Lee, Hyeonseo Cho, Hyunseung Kim, Donghu Kim, Dugki Min, Jaegul Choo, Clare Lyle
Strong Generalization Plasticity Rule

May 27, 2024

Theories of synaptic memory consolidation and intelligent plasticity for continual learning
Friedemann Zenke, Axel Laborieux
Continual LEArning Theoretical Understanding Plasticity Rule Synaptic Plasticity Memory Consolidation Neural Plasticity Synaptic Dynamic

May 23, 2024

Contribute to balance, wire in accordance: Emergence of backpropagation from a simple, bio-plausible neuroplasticity rule
Xinhao Fan, Shreesh P Mysore
Back Propagation Path Breaking Emergence Balancing Strategy Plasticity Rule Visual Circuit Neural Plasticity Stiff Metal Wire

May 22, 2024

EchoSpike Predictive Plasticity: An Online Local Learning Rule for Spiking Neural Networks
Lars Graf, Zhe Su, Giacomo Indiveri
Neural Network Spiking Neural Network Neuromorphic Computing Plasticity Rule Neuromorphic Processor Local Learning Rule

April 3, 2024

Can We Understand Plasticity Through Neural Collapse?
Guglielmo Bonifazi, Iason Chalas, Gian Hess, Jakub Łucki
Deep Learning Neural Collapse Total Correlation Plasticity Rule Regularization Approach Plasticity Loss

March 31, 2024

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
Mohamed Elsayed, A. Rupam Mahmood
Continual LEArning Representation Learning Catastrophic Forgetting Continual Learning Plasticity Rule Novel Stealth Loss

March 27, 2024

Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning
Wenzhuo Liu, Fei Zhu, Cheng-Lin Liu
Self Supervised Learning Self Supervised Continual LEArning Core Stability Convolutional Layer Plasticity Rule Batch Normalization Layer Self Supervised Continual Learning

March 20, 2024

Network bottlenecks and task structure control the evolution of interpretable learning rules in a foraging agent
Emmanouil Giannakakis, Sina Khajehabdollahi, Anna Levina
Agent Smith Specie Evolution Plasticity Rule Task Specification Stability Plasticity Interpretable Rule Biological Learning Network Bottleneck

March 4, 2024

Hybrid data-driven and physics-informed regularized learning of cyclic plasticity with Neural Networks
Stefan Hildebrand, Sandra Klinge
Neural Network LeArning Abstract Efficient Hybrid Plasticity Rule Mapping Algorithm Material Modeling

March 1, 2024

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
Michal Nauman, Michał Bortkiewicz, Piotr Miłoś, Tomasz Trzciński, Mateusz Ostaszewski, Marek Cygan
Reinforcement Learning Regularization Model Policy Reinforcement Learning Model Overfitting Regularization Technique Plasticity Rule Soft Actor Critic Policy Algorithm

Plasticity Rule

Papers

Plasticity Loss in Deep Reinforcement Learning: A Survey

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

Self-Normalized Resets for Plasticity in Continual Learning

Gradient-Free Supervised Learning using Spike-Timing-Dependent Plasticity for Image Recognition

Neural Network Plasticity and Loss Sharpness

Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing

Accounting for plasticity: An extension of inelastic Constitutive Artificial Neural Networks

Investigating Critical Period Effects in Language Acquisition through Neural Language Models

Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning

Unsupervised representation learning with Hebbian synaptic and structural plasticity in brain-like feedforward neural networks

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks

Theories of synaptic memory consolidation and intelligent plasticity for continual learning

Contribute to balance, wire in accordance: Emergence of backpropagation from a simple, bio-plausible neuroplasticity rule

EchoSpike Predictive Plasticity: An Online Local Learning Rule for Spiking Neural Networks

Can We Understand Plasticity Through Neural Collapse?

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning

Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning

Network bottlenecks and task structure control the evolution of interpretable learning rules in a foraging agent

Hybrid data-driven and physics-informed regularized learning of cyclic plasticity with Neural Networks

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning