advent-of-code-2023

byte-pair-encoding

Byte pair encoding tokenizer as used in some large language models.

clabrugere

clabrugere.github.io

ctr-prediction

Implementation of some state-of-the-art deep learning architectures for CTR prediction tasks, both in Pytorch and Tensorflow

datasets

dynamic-time-warping

Fast implementation of Dynamic Time Warping algorithm using numba

ecommerce-dash

Example of a Dash application applied to e-commerce data to represent key metrics in the form of an interactive dashboard

evidential-deeplearning

Implementation of "Evidential Deep Learning to Quantify Classification Uncertainty" proposing a method to quantify uncertainty in a neural network.

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

fastapi-fraud-detection

Example of a fully packaged ML model in a Docker image and exposed as a REST API using FastAPI framework

final-mlp

Implements SOTA architecture for CTR predictions tasks, both in Pytorch and Tensorflow

m5-forecasting

Some strategies of hierarchical time series forecasting in the context of the M5 competition hosted on Kaggle

multitask-learning

Tensorflow implementation of three architectures for multi-task learning, a paradigm to learn different prediction tasks jointly using one model

numpy-basics

10 or so machine learning algorithms implemented using Numpy only

plant-pathology-classification

Implementation of the Wide-ResNet architecture in Pytorch, as described in the original paper and used on a plant's disease image classification problem

portfolio-balance

Streamlit application to optimally re-balance a portfolio given a target allocation, current positions and market prices

pytorch-scarf

Implementation of SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption in Pytorch, a model learning a representation of tabular data using contrastive learning. It is inspired from SimCLR and uses a similar architecture and loss.

randomized-prior-net

Simple and efficient way of performing deep ensembling to improve robustness as well as estimate uncertainty

scratch-llm

Implements a LLM similar to Meta's Llama 2 from the ground up in PyTorch, for educational purposes.

ssl-images

Implements VICReg, NT-Xent and DCL losses for contrastive self-supervised learning to generate semantically meaningful representations of images without labels.

streamlit-nav

Custom component in Typescript and Python for multipage navigation in Streamlit applications

template-datascience

cookiecutter template for standard data science and machine learning projects in python.

web-lazy-rebalance

WIP - Web application to optimally rebalance a portfolio (greedily) powered by Svelte

wukong-recommendation

Implements the paper "Wukong: Towards a Scaling Law for Large-Scale Recommendation" from Meta.