BioTorch is a PyTorch framework specializing in biologically plausible learning algorithms

The Hierarchical Intrinsically Motivated Agent (HIMA) is an algorithm that is intended to exhibit an adaptive goal-directed behavior using neurophysiological models of the neocortex, basal ganglia, and thalamus.

PyTorch implementation of the paper "Spatio-Temporal Decoupled Learning for Spiking Neural Networks"

🐣 Code for my master thesis "Biologically Plausible Deep Learning through Neuroevolution"

PyTorch implementation of the paper "Scaling Supervised Local Learning with Augmented Auxiliary Networks"

Awesome list of research publications and media on biologically-motivated learning algorithms.

Predictive Coding with errors, not states

Biologically plausible cognitive architecture: structural memory, thought formation, and language without gradients or backpropagation

Pytorch Implementation, Experiments and Exploration of Biologically Plausible Neural Networks as a final project of CLPS1291 @ Brown

This repo is the implementation of perturbation based algorithms for training neural networks - we evaluate the scalability of node perturbation with network width and depth on modern datasets such as MNIST, CIFAR, etc.

Bridge Cursor subscriptions to run Claude Code seamlessly using Anthropic and OpenAI APIs without needing a separate Anthropic key.

Replicating the results of a paper on underlying mechanisms of feedback alignment .

GAP is a biologically plausible learning algorithm designed for Dynamically Gated Analog Crossbars (DGAC). It bridges the gap between the energy efficiency of local Hebbian learning and the global optimization power of backpropagation by utilizing dynamic Riemannian curvature.