Stars
NMA Computational Neuroscience course
📐 Compute distance between sequences. 30+ algorithms, pure python implementation, common interface, optional external libs usage.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
Pretrained TorchVision models on CIFAR10 dataset (with weights)
Deep Clustering for Unsupervised Learning of Visual Features
A simple way to calibrate your neural network.
Code & data accompanying the KDD 2017 paper "KATE: K-Competitive Autoencoder for Text"
Mixture-of-Embeddings-Experts
🐍 An improved Python library to control i3wm and sway.
My personal dotfiles (how do these have so many stars?)
Meta package for the Regolith Desktop Environment
Rich is a Python library for rich text and beautiful formatting in the terminal.
Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.
Interpretability Methods for tf.keras models with Tensorflow 2.x
Pytorch Lightning code guideline for conferences
This is where I put all my work in Natural Language Processing
Deep Embedded Clustering with Data Augmentation (DEC-DA). Performance on MNIST (acc=0.985, nmi=0.960).
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
A Python Package for Density Ratio Estimation
Super easy library for BERT based NLP models
Layers Outputs and Gradients in Keras. Made easy.
Simple and easily configurable grid world environments for reinforcement learning
Attributing predictions made by the Inception network using the Integrated Gradients method
Make huge neural nets fit in memory
To Trust Or Not To Trust A Classifier. A measure of uncertainty for any trained (possibly black-box) classifier which is more effective than the classifier's own implied confidence (e.g. softmax pr…
Experiments towards neural network theorem proving
A technical report on convolution arithmetic in the context of deep learning