머신러닝 · GitHub

An elegant PyTorch deep reinforcement learning library.

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

《深度学习与计算机视觉》配套代码

PyTorch를 사용한 딥러닝 개발과 연구를 빠르게 시작할 수 있도록 돕는 오픈 소스 책입니다. 책에 포함된 PyTorch 튜토리얼은 모두 테스트를 거쳐 정상적으로 실행되는 것을 확인했습니다.

머신러닝 엔지니어가 되기 위한 종합적인 일일 학습 계획.

• "You can, but it is far more difficult than when I got into the field." Drac Smith
• "I'm hiring machine learning experts for my team and your MOOC will not get you the job (there is better news below). In fact, many people with a master's in machine learning will not get the job because they (and most who have taken MOOCs) do not have a deep understanding that will help me solve my problems." Ross C. Taylor

🚀5초 만에 음성을 복제하여 임의의 음성을 실시간으로 생성

Stable Diffusion WebUI Colab

대규모 AI 모델을 더 저렴하고, 더 빠르고, 더 쉽게 이용할 수 있게 만듭니다

• Data Parallelism
• Pipeline Parallelism

Stanford의 Alpaca 모델을 학습하고 데이터를 생성하기 위한 코드와 문서입니다.

The central nervous system and backend orchestrator for Fractal. It handles multi-tenant task scheduling, real-time TFLOPs budgeting, and federated weight aggregation using FedAvg.

• Edge AI & Mobile Compute Orchestration Spotlight: Architectural overview and visual demonstration spotlighting on-device edge intelligence, distributed training rounds, and decentralized compute harvesting across mobile devices.

C++ 코어와 Python으로 확장할 수 있는 50개 이상의 노드를 제공하는 고성능 AI 파이프라인 엔진입니다. 13개 이상의 모델 제공업체, 8개 이상의 벡터 데이터베이스, 에이전트 오케스트레이션을 지원하며 IDE에서 LLM 워크플로를 구축하고 디버깅하고 확장할 수 있습니다. VS Code 확장, TypeScript/Python SDK, Docker 배포를 포함합니다.

• Rocket Builder - Drag, connect, and configure nodes visually, no boilerplate. Real-time observability tracks token usage, LLM calls, latency, and execution. Pipelines are portable JSON, version-controllable, shareable, and runnable anywhere.
• High-Performance C++ Runtime - Native multithreading purpose-built for the throughput demands of AI and data workloads. No bottlenecks, no compromises for production scale.

Static reproducibility checks, experiment replay, and verification for ML pipelines.

This repository provides DINOSim, a method that leverages the DINOv2 foundation model for zero-shot object detection and segmentation in bioimage analysis. DINOSim uses pretrained DINOv2 embeddings to compare patch similarities, allowing it to detect and segment unseen objects in complex datasets with minimal annotations.

Aaryan Samanta: machine learning for biology and medicine. First-author papers, mentored research, USACO Platinum, and AI Ethos, Inc.

An efficient Python toolkit for Abductive Learning (ABL), a novel paradigm that integrates machine learning and logical reasoning in a unified framework.

🧠 Sentiment Sense: Advanced NLP dashboard using DistilBERT & Zero-Shot (BART) for Aspect-Based Sentiment Analysis. Detects business topics (Food, Service, Price) & emotional context in real-time. Built for enterprise feedback processing. 🚀

• Dual-Model Pipeline: Combines a DistilBERT transformer for sentiment with a BART-Large model for zero-shot topic classification.
• Aspect-Based Analysis (ABSA): Automatically identifies specific categories (Food, Service, Price, etc.) mentioned in the text without manual labeling.