Materials from fMRI data analysis course for cognitive science students.

Matplotlib styles for scientific plotting

A simple script exporting chats from a rocket chat instance using the public REST API. Useful if no administrative access is possible.

An Numpy and PyTorch Implementation of CKA-similarity with CUDA support

1st place solution for the UW Neural Data Challenge

Multilabel classification on a subset of COCO captions using BiLSTM, CNN and Faster-RCNN components.

Code for Neural Population Control

A collection of infrastructure and tools for research in neural network interpretability.

Re-implementation of part of Lucid in TensorFlow 2, for feature visualization

Neural network visualization toolkit for tf.keras

Code for "Learning Perceptually-Aligned Representations via Adversarial Robustness"

repo for 2019 neurips paper "Metamers of neural networks reveal divergence from human perceptual systems."

An LLM-based autonomous agent controlling real-world applications via RESTful APIs

This repo contains documentation and code needed to use PACO dataset: data loaders and training and evaluation scripts for objects, parts, and attributes prediction models, query evaluation scripts…

Code release for Hu et al. Learning to Reason: End-to-End Module Networks for Visual Question Answering. in ICCV, 2017

PhyCV: The First Physics-inspired Computer Vision Library

Official code for NeurRIPS 2020 paper "Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D"

🌎 machine learning tutorials (mainly in Python3)

Tips and tricks for working with Large Language Models like OpenAI's GPT-4.

Official code for the paper "Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks".

Official Code for ICLR2022 Paper: Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

Pretrained models for "What Makes Instance Discrimination Good for Transfer Learning?".

Implementation of ICML (Oral) 2022 paper "Measuring Representational Robustness of Neural Networks Through Shared Invariances"

The Transformational Measures (TM) library allows neural network researchers to evaluate the invariance and equivariance of their models with respect to a set of transformations. Support for Pytorc…

Systems Neuroscience Computing in Python: user-friendly analysis of large-scale electrophysiology data

Image restoration with neural networks but without learning.

A collection of libraries to optimise AI model performances