Awesome list of research publications and media on biologically-motivated learning algorithms.
| Publications | Media |
|---|---|
| 2021, 2020, 2019, 2018, 2017, 2016, 2015, 2014, 2012, 2008, 2003, 1996, 1994, 1991, 1989, 1987 |
Podcasts |
Align, then memorise: the dynamics of learning with feedback alignment [arXiv]
Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms [arXiv]
Credit Assignment Through Broadcasting a Global Error Vector [arXiv]
Credit Assignment in Neural Networks through Deep Feedback Control [arXiv]
On the relationship between predictive coding and backpropagation [arXiv]
Predictive Coding Can Do Exact Backpropagation on Any Neural Network [arXiv]
Tourbillon: a Physically Plausible Neural Architecture [arXiv]
A Theoretical Framework for Target Propagation [arXiv]
Backpropagation and the brain [Nature]
Biological credit assignment through dynamic inversion of feedforward networks [arXiv]
Can the Brain Do Backpropagation? — Exact Implementation of Backpropagation in Predictive Coding Networks [PDF]
Contrastive Similarity Matching for Supervised Learning [arXiv]
Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future [arXiv]
Differentially Private Deep Learning with Direct Feedback Alignment [arXiv]
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures [arXiv]
GAIT-prop: A biologically plausible learning rule derived from backpropagation of error [arXiv]
Identifying Learning Rules From Neural Network Observables [arXiv]
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks [arXiv]
Learning to Learn with Feedback and Local Plasticity [arXiv]
Learning to solve the credit assignment problem [arXiv]
Spike-based causal inference for weight alignment [arXiv]
Two Routes to Scalable Credit Assignment without Weight Symmetry [arXiv]
A deep learning framework for neuroscience [Nature]
Biologically plausible deep learning -- but how far can we go with shallow networks? [arXiv]
Deep Learning With Asymmetric Connections and Hebbian Updates [arXiv]
Deep Learning without Weight Transport [arXiv]
Direct Feedback Alignment with Sparse Connections for Local Learning [arXiv]
Efficient Convolutional Neural Network Training with Direct Feedback Alignment [arXiv]
Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks [arXiv]
Recurrence is required to capture the representational dynamics of the human visual system [PDF]
Principled Training of Neural Networks with Direct Feedback Alignment [arXiv]
Putting An End to End-to-End: Gradient-Isolated Learning of Representations [arXiv]
The HSIC Bottleneck: Deep Learning without Back-Propagation [arXiv]
Theories of Error Back-Propagation in the Brain [PDF]
Training Neural Networks with Local Error Signals [arXiv]
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures [arXiv]
Biologically Motivated Algorithms for Propagating Local Target Representations [arXiv]
Biologically-plausible learning algorithms can scale to large datasets [arXiv]
Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like? [bioRxiv]
CORnet: Modeling the Neural Mechanisms of Core Object Recognition [PDF]
Conducting Credit Assignment by Aligning Local Representations [arXiv]
Control of synaptic plasticity in deep cortical networks [Nature]
Deep Supervised Learning Using Local Errors [arXiv]
Dendritic cortical microcircuits approximate the backpropagation algorithm [arXiv]
Feedback alignment in deep convolutional networks [arXiv]
Unsupervised Learning by Competing Hidden Units [arXiv]
An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity [Link]
Decoupled Neural Interfaces using Synthetic Gradients [arXiv]
Deep Learning with Dynamic Spiking Neurons and Fixed Feedback Weights [PDF]
Dendritic error backpropagation in deep cortical microcircuits [arXiv]
Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines [arXiv]
Explaining the Learning Dynamics of Direct Feedback Alignment [PDF]
SuperSpike: Supervised learning in multi-layer spiking neural networks [arXiv]
Towards a Biologically Plausible Backprop [arXiv]
Towards deep learning with segregated dendrites [arXiv]
Understanding Synthetic Gradients and Decoupled Neural Interfaces [arXiv]
Direct Feedback Alignment Provides Learning in Deep Neural Networks [arXiv]
Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation [arXiv]
Random synaptic feedback weights support error backpropagation for deep learning [Nature]
Toward an Integration of Deep Learning and Neuroscience [arXiv]
Using goal-driven deep learning models to understand sensory cortex [Nature]
Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing. [PDF]
Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream [arXiv]
How Important is Weight Symmetry in Backpropagation? [arXiv]
STDP as presynaptic activity times rate of change of postsynaptic activity [arXiv]
Towards Biologically Plausible Deep Learning [arXiv]
Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation [PDF]
Difference Target Propagation [arXiv]
How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation [arXiv]
Kickback cuts Backprop's red-tape: Biologically plausible credit assignment in neural networks [arXiv]
Performance-optimized hierarchical models predict neural responses in higher visual cortex [PDF]
Random feedback weights support learning in deep neural networks [arXiv]
Adaptive Optimal Control Without Weight Transport [PDF]
Supervised Learning in Multilayer Spiking Neural Networks [arXiv]
Spike timing-dependent plasticity: a Hebbian learning rule [PubMed]
Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network [PDF]
Learning in Spiking Neural Networks by Reinforcement of Stochastic Synaptic Transmission [PDF]
Biologically Plausible Error-driven Learning using Local Activation Differences: The Generalized Recirculation Algorithm [PDF]
Backpropagation without weight transport [IEEE]
A more biologically plausible learning rule for neural networks [PDF]
Is backpropagation biologically plausible? [IEEE]
Competitive Learning: From Interactive Activation to Adaptive Resonance [Link]
Learning Representations by Recirculation [PDF]
Biologically Plausible Neural Networks - Dr. Simon Stringer [Link]
Dileep George: Brain-Inspired AI | Lex Fridman Podcast [Link]
Engineering a Less Artificial Intelligence with Andreas Tolias [Link]
Matt Botvinick: Neuroscience, Psychology, and AI at DeepMind | Lex Fridman Podcast [Link]
Spiking Neural Nets and ML as a Systems Challenge with Jeff Gehlhaar [Link]
Spiking Neural Networks: A Primer with Terrence Sejnowski [Link]
The Biological Path Towards Strong AI with Matthew Taylor [Link]