neuro-ai

⚡ 📚 Papers and other material for getting started with Neuro-AI! 🧠 💥

A curated repository of Neuro-AI papers.

[TPAMI, 2023] Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving

PyTorch-native framework for fault-tolerant distributed training of foundation models on AI clusters

Movie-trained transformer reveals novel response properties to dynamic stimuli in mouse visual cortex

[NeurIPS 2024] 🥉 ViV1T submission in the Sensorium 2023 challenge

AURA is an ML-driven advanced EEG-based Brain-Computer Interface leveraging ESP32, ADS1299, and ML for real-time mental-state mapping and early disease prediction. Achieving 93% accuracy, it pioneers assistive tech for non-verbal communication and IoT integration.

spiking neural activity data from rodents

Codebase for the Neurips 2023 spotlight paper "Curriculum Learning with Infant Egocentric Videos"

A language for AI: intent-driven programming

spiking neural activity data from primates

A deep learning and neuroscience project for processing fMRI data. Uses Nilearn for functional connectivity mapping and PyTorch for model training, specifically optimized for Apple Silicon (M1/M2/M3) via MPS acceleration. Features automated preprocessing of 48x48 connectivity matrices into 2,304-feature vectors. Built with Python 3.13.

Drosophila-inspired Temple Runner with 3D Neural Observatory, DeepMind flybody, and connectome circuits

Fruit Fly (Drosophila MaleCNS v1.0) biological connectome playing Microsoft Minesweeper with real-time 3D WebGL neural activity HUD. Built in PyTorch & Three.js.

This repo contains necessary code and sample data for reproducing the figures in paper Polarity is all you need to learn and transfer faster.

An interactive app that analyzes your personality profile using KMeans and visualizes it with radar charts

Naturalistic fMRI corpus (100 top-tier papers, 2021-2026) + NotebookLM-integrated research synthesis pipeline. 20 expert queries across 7 categories surface SOTA, outstanding questions, and AI applications.

An Oracle SQL knowledge base (14-table, 3NF) mapping structural, functional, and computational parallels between brain structures and artificial neural networks, referenced against 57 published papers with funding-bias analysis.

An open-source framework for leveraging representations from speech and vision foundation models to analyze neuroimaging data through voxel-wise encoding analyses.

Notes and ideas from NAISys 2020