Backpropagation and the brain

2020/04/17 by Timothy Lillicrap, Timothy P. Lillicrap, Adam Santoro +4 · 74 citations
Computer Science · Engineering · Neuroscience · #Advanced Memory and Neural Computing #Neural Networks and Applications #Neural dynamics and brain function

paper · doi:10.1038/s41583-020-0277-3

crossref issued 2020/04/17 · crossref published 2020/04/17 · crossref published-online 2020/04/17 · openalex publication_date 2020/04/17 · crossref created 2020/04/17 · crossref published-print 2020/06/01 · crossref deposited 2023/09/30 · openalex created_date 2025/10/10 · crossref indexed 2026/07/28 · openalex updated_date 2026/08/02

Citations

• Random feedback weights support learning in deep neural networks
• Distinct functions for direct and transthalamic corticocortical connections
• Simple memory: a theory for archicortex
• Continuous control with deep reinforcement learning
• Pixel Recurrent Neural Networks
• DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
• An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity
• Behavioral time scale synaptic plasticity underlies CA1 place fields

Cited by

• Deriving Differential Target Propagation from Iterating Approximate Inverses
• Entorhinal cortex directs learning-related changes in CA1 representations
• Theory before the test: How to build high-verisimilitude explanatory theories in psychological science
• Vectorized instructive signals in cortical dendrites
• Bidirectional synaptic plasticity rapidly modifies hippocampal representations
• Laminar-specific cortico-cortical loops in mouse visual cortex
• Neko: a Library for Exploring Neuromorphic Learning Rules
• Theory Before the Test: How to Build High-Verisimilitude Explanatory Theories in Psychological Science
• Dopamine-driven synaptic credit assignment in neural networks
• A Unified Perspective on Optimization in Machine Learning and Neuroscience: From Gradient Descent to Neural Adaptation
• Does Feedback Alignment Work at Biological Timescales?
• A general framework for interpretable neural learning based on local information-theoretic goal functions
• Navigate in Demanding Missions: Integrating Human Intelligence and Brain-Inspired Intelligence
• Artificial creativity: can there be creativity without cognition?
• A deep learning theory for neural networks grounded in physics
• Biological credit assignment through dynamic inversion of feedforward networks
• Investigating the Scalability and Biological Plausibility of the Activation Relaxation Algorithm
• Dale meets Langevin: A Multiplicative Denoising Diffusion Model
• A Biologically Interpretable Cognitive Architecture for Online Structuring of Episodic Memories into Cognitive Maps
• Can Local Learning Match Self-Supervised Backpropagation?
• Key-value memory in the brain
• A contrastive rule for meta-learning
• Forward Only Learning for Orthogonal Neural Networks of any Depth
• Dual-Timescale Hebbian Accumulators for Online Spiking Neural Network Decoding in Intracortical Brain Machine Interfaces
• Traces Propagation: Memory-Efficient and Scalable Forward-Only Learning in Spiking Neural Networks
• On-Chip Error-triggered Learning of Multi-layer Memristive Spiking Neural Networks
• Artificial neural networks for neuroscientists: A primer
• Assessing Consciousness-Related Behaviors in Large Language Models Using the Maze Test
• Self-organized learning emerges from coherent coupling of critical neurons
• Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability
• Dynamical Mechanism of Sampling-based Stochastic Inference under Probabilistic Population Codes
• Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis
• Statistical Learning in Speech: A Biologically Based Predictive Learning Model
• MAN++: Scaling Momentum Auxiliary Network for Supervised Local Learning in Vision Tasks
• From Artificial Intelligence to Brain Intelligence: The basis learning and memory algorithm for brain-like intelligence
• Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learning
• Local imperfect feedback control in non-equilibrium biophysical systems enabled by thermodynamic constraints
• Episodic Memory in Animals
• Model-free Optical Processors using In Situ Reinforcement Learning with Proximal Policy Optimization
• Hierarchy or Heterarchy? A Theory of Long-Range Connections for the Sensorimotor Brain
• A Theoretical Framework for Target Propagation
• Object Based Attention Through Internal Gating
• Convergence and Alignment of Gradient Descent with Random Backpropagation Weights
• Fully analog end-to-end online training with real-time adaptibility on integrated photonic platform
• Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories
• Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Example
• A conclusive remark on linguistic theorizing and language modeling
• Geospatial Mechanistic Interpretability of Large Language Models
• One-Time Soft Alignment Enables Resilient Learning without Weight Transport
• MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents
• GAIT-prop: A biologically plausible learning rule derived from backpropagation of error
• Ubiquity of Emergent Hebbian Dynamics in Regularized Learning
• Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory
• From the perceptron to the cerebellum
• A biologically plausible neural network for local supervision in cortical microcircuits
• Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses
• Artificial intelligence without restriction surpassing human intelligence with probability one: Theoretical insight into secrets of the brain with AI twins of the brain
• Predictive coding feedback results in perceived illusory contours in a recurrent neural network
• Self-Learning Machines Based on Hamiltonian Echo Backpropagation
• Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation
• Contrastive Similarity Matching for Supervised Learning
• Learning to infer in recurrent biological networks
• Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks
• The curious case of developmental BERTology: On sparsity, transfer learning, generalization and the brain
• Learning a Vector-Symbolic Model for Socio-Cultural Tasks
• The Neuroscience of Transformers
• This is how the Neocortex Learns
• Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data
• Untrained CNNs Match Backpropagation at V1: A Systematic RSA Comparison of Four Learning Rules Against Human fMRI
• Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization
• The Why, What, and How of Artificial General Intelligence Chip Development
• Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning
• Correlation-invariant synaptic plasticity
• Boosting Reservoir Computing with Brain-inspired Adaptive Dynamics
• Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescaling
• On the Adversarial Robustness of Spiking Neural Networks Trained by Local Learning