AlexandruBurlacu

awesome-bigdata

A curated list of awesome big data frameworks, ressources and other awesomeness.

machine-learning-interview

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

BentoML

The easiest way to serve AI/ML models in production - Build Model Inference Service, LLM APIs, Multi-model Inference Graph/Pipelines, LLM/RAG apps, and more!

handbook

Basecamp Employee Handbook

kraken

P2P Docker registry capable of distributing TBs of data in seconds

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

serving

Kubernetes-based, scale-to-zero, request-driven compute

mmselfsup

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

imagehash

A Python Perceptual Image Hashing Module

gtor

A General Theory of Reactivity

kaggle-web-traffic

1st place solution

Physics-Based-Deep-Learning

Links to works on deep learning algorithms for physics problems, TUM-I15 and beyond

awesome-AutoML

Curating a list of AutoML-related research, tools, projects and other resources

slimevolleygym

A simple OpenAI Gym environment for single and multi-agent reinforcement learning

GPBoost

Combining tree-boosting with Gaussian process and mixed effects models

spark-standalone-cluster-on-docker

Learn Apache Spark in Scala, Python (PySpark) and R (SparkR) by building your own cluster with a JupyterLab interface on Docker. :zap:

cloudburst

A stateful serverless platform

samples

Microservices Security in Action Book Samples

erlang-patterns

LambdaPad source files for erlangpatterns.org

sps

Official code for the Stochastic Polyak step-size optimizer

blockhash-python

Implementation of perceptual image hash calculation in Python

themis-ml

A library that implements fairness-aware machine learning algorithms

STL10

Python utilities for reading the STL-10 dataset: http://cs.stanford.edu/~acoates/stl10/

dagger

Experiment orchestration

loss-surface-simplexes

observatory

:octocat: :star2: Awesome List of my own!

nips.cocob.pytorch

PyTorch implementation of the NIPS'17 paper Training Deep Networks without Learning Rates Through Coin Betting.

MiLeNAS

MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation. Published in CVPR 2020

code_review

fewshotDatasetDesign

The paper studies the problem of learning to recognize a new class of objects from a very small number of labeled images. This is called few-shot learning. Previous work in the literature focused on designing new algorithms that allow to learn to generalize to new unseen classes.In this work, we consider the impact of the dataset that we train on, and experiment with some dataset manipulations to see which trade-offs are important in the design of a dataset aimed at few-shot learning.