Library · 10-bio-inspired-optimization

Bio-inspired optim

TitlePeerLink
Evolution Strategies at Scale: LLM Fine-Tuning Beyond RL◦ preprintarxiv.org/abs/2509.24372
TD-ES: Bounded-Support Evolution Strategies for Policy Refinement◦ preprintarxiv.org/abs/2511.09923
EA4LLM: Gradient-Free LLM Optimization via Evolutionary Algorithms◦ preprintarxiv.org/abs/2510.10603
Low-Rank Factorizations are Indirect Encodings for Deep Neuroevolution◦ preprintarxiv.org/abs/2504.03037
Towards Scaling Deep NNs with Predictive Coding (μPC)◦ preprintarxiv.org/abs/2510.23323
Benchmarking Predictive Coding Networks — Made Simple (PCX)◦ preprintarxiv.org/abs/2407.01163
Adaptive Spatial Goodness Encoding (ASGE): Scaling Forward-Forward◦ preprintarxiv.org/abs/2509.12394
Forward Target Propagation (FTP)◦ preprintarxiv.org/abs/2506.11030
Self-Contrastive Forward-Forward (SCFF)✓ peernature.com/articles/s41467-025-61037-0
A Review of Neuroscience-Inspired Machine Learning◦ preprintarxiv.org/abs/2403.18929
TensorNEAT: GPU-accelerated NEAT (JAX)◦ preprintarxiv.org/abs/2504.08339
Optimizing Deep RL through Vectorized & Parallel NeuroEvolutionsciencedirect.com/science/article/abs/pii/S…
EvoX: Distributed GPU Framework for Scalable Evolutionary Computation◦ preprintarxiv.org/abs/2301.12457
Direct Feedback Alignment Provides Learning in Deep NNs (DFA)◦ preprintarxiv.org/abs/1609.01596
Direct Feedback Alignment With Sparse Connections for Local Learningpmc.ncbi.nlm.nih.gov/articles/PMC6542988/
GrAPE: Scaling Direct Feedback Learning w/ Jacobian Alignmentopenreview.net/forum?id=kasbbmwk3s
e-prop: a solution to the learning dilemma for recurrent spiking nets✓ peernature.com/articles/s41467-020-17236-y
Scaling Equilibrium Propagation to Deeper Architectures◦ preprintarxiv.org/abs/2509.26003
Information-bottleneck Hebbian learning rulepmc.ncbi.nlm.nih.gov/articles/PMC11137249/
Predictive Coding as a Neuromorphic Alternative to BP: A Critical Evaluation◦ preprintarxiv.org/abs/2304.02658
Taming the chaos gently: predictive alignment in recurrent nets (Asabuki & Clopath)✓ peernature.com/articles/s41467-025-61309-9
A Backpropagation-Free Feedback-Hebbian Network for Continual Learning Dynamics◦ preprintarxiv.org/abs/2601.06758
Brain-inspired replay for continual learning with ANNs (van de Ven)✓ peernature.com/articles/s41467-020-17866-2
Titans: Learning to Memorize at Test Time◦ preprintarxiv.org/abs/2501.00663
Reward Prediction Error Prioritisation in Experience Replay (RPE-PER)◦ preprintarxiv.org/abs/2501.18093
SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning◦ preprintarxiv.org/pdf/2511.22367
Phasor Agents: three-factor plasticity + sleep-staged replay◦ preprintarxiv.org/abs/2601.04362
Inferring neural activity before plasticity — prospective configuration (Song, Bogacz)✓ peernature.com/articles/s41593-023-01514-1
BioNAS — NAS over mixed per-layer bio-inspired learning rules◦ preprintarxiv.org/abs/2507.13485
μPC — scaling predictive coding to 100+ layers (Depth-μP)◦ preprintarxiv.org/abs/2505.13124
PCN trained on ImageNet via equilibrium propagation◦ preprintarxiv.org/abs/2606.03584
NeuroTrain — local-learning-rule benchmark for SNNs◦ preprintarxiv.org/abs/2605.15058
The backpropagation algorithm implemented on spiking neuromorphic hardware
FPTT — accurate online training of dynamical SNNs (Forward Propagation Through Time)
BrainTrace — model-agnostic linear-memory online learning in SNNs
A stable, fast, fully automatic learning algorithm for PC networks (incremental PC)
DFA Scales to Modern Deep Learning Tasks and Architectures◦ preprintarXiv:2006.12878
Holomorphic Equilibrium Propagation
Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training (Chen)◦ preprintarxiv.org/abs/2606.06539
Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines◦ preprintarxiv.org/abs/2510.12934
Energy-Efficient DL Without Backprop: A Rigorous Evaluation of Forward-Only Algorithms◦ preprintarxiv.org/abs/2511.01061
Can Local Learning Match Self-Supervised Backpropagation? (CLAPP++)◦ preprintarxiv.org/abs/2601.21683
Intrinsic-Noise Consolidation (Doob-barrier-conditioned diffusion)◦ preprintarxiv.org/abs/2607.06924
Synaptic plasticity: taming the beast✓ peerdoi.org/10.1038/81453
Spike timing-dependent plasticity of neural circuits✓ peerdoi.org/10.1016/j.neuron.2004.09.007
Synaptic modifications dependent on spike timing (STDP)✓ peerdoi.org/10.1523/JNEUROSCI.18-24-10464.1998
Long-lasting potentiation of synaptic transmission (LTP)✓ peerdoi.org/10.1113/jphysiol.1973.sp010273
Bio-inspired AI: Integrating Biological Complexity into Artificial Intelligence◦ preprintarxiv.org/abs/2411.15243
Direct Feedback Alignment with sparse connections for local learning✓ peerdoi.org/10.3389/fnins.2019.00525
An information-bottleneck-based Hebbian learning rule✓ peerdoi.org/10.3389/fncom.2024.1240348
Ubiquity of Emergent Hebbian Dynamics in Regularized Learningarxiv.org/abs/2505.18069
Adaptive learning via surprise gated attractor switchingdoi.org/10.1101/2025.03.13.643078
Parallel processing of orthogonal manifolds enables zero-shot composition in recurrent networksdoi.org/10.64898/2026.06.14.732142