neuroscience-inspired-ai

A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...

Actively developed Hierarchical Temporal Memory (HTM) community fork (continuation) of NuPIC. Implementation for C++ and Python

Code behind the work "Single Cortical Neurons as Deep Artificial Neural Networks", published in Neuron 2021

Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization

Emergent behaviour and neural dynamics in artificial agents tracking odour plumes

Axon is a spiking, biologically-based neural model driven by predictive error-driven learning, for systems-level models of the brain

ConvRNN Model Zoo: ImageNet pre-trained convolutional recurrent neural networks

Temporal Neural Networks

Neuromodulatory Control Networks (NCNs), a novel LLM architectural modification inspired by the neuromodulatory systems in the vertebrate brain.

Code for our AAMAS 2020 paper: "A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry".

Code behind the work "Multiple Synaptic Contacts Combined with Dendritic Filtering Enhance Spatio-Temporal Pattern Recognition of Single Neurons", bioRxiv 2022

Models of Mouse Vision: Self-supervised pre-trained networks and training code (PyTorch)

"The Unreasonable Effectiveness of Sparse Dynamic Synapses for Continual Learning" paper project.

Solving catastrophic forgetting with Recursive Time architecture, Active Sleep (generative replay), and Temporal LoRA. Proving the "Lazarus Effect" in neural networks.

Implementation of BIMRL: Brain Inspired Meta Reinforcement Learning - Roozbeh Razavi et al. (IROS 2022)

Artificial Biological Intelligence

🧠 Build a cutting-edge AI agent with Project Synapse that enables strategic thought and multi-turn collaborative dialogue for innovation and discovery.

Code for our NeuroAI tactile paper

Quantum neural network research implementing multi-dimensional neuron representations. Explores theoretical integration of quantum computing principles into neural systems to investigate emergent cognition and consciousness.

Official Repository of the "How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy" Paper