Maschinelles Lernen · GitHub

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation (USENIX Security '23)

Locally Private Graph Neural Networks (ACM CCS 2021)

Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation

SOTA Semantic Segmentation Models in PyTorch

• Medical Image Segmentation (Coming Soon)
• 15+ SOTA Backbones

FSQ K-line foundation model for China A-share stock selection, with a containerised multi-factor research platform: data governance, factor research and observability.

• Finance-native pre-training. 100 % financial corpus: 3.06 billion raw K-lines across 7 frequencies (1-minute to weekly), including 5,872 delisted stocks to avoid survivorship bias.
• FSQ parallel tokenization. Four bounded scalars with levels [8, 8, 8, 5] give 2,560 implicit states with no codebook, so codebook collapse cannot happen. Limit-up/down bars, gaps and volume spikes map to edge levels instead of being flattened. 71.4 % of joint states are used, with normalised entropy 0.87.

Code for the ICPR 2020 paper: "CURL: Neural Curve Layers for Image Enhancement"

DeepLPF (CVPR 2020): interpretable image enhancement with learned cubic, graduated and elliptical filters. pip install, then 'deeplpf enhance photo.jpg'.

dl4j 基础教程 配套视频：https://space.bilibili.com/327018681/#/

Handwriting Synthesis with RNNs ✏️

Kaggle | Web Traffic Forecasting 📈

Machine Learning for Go

Exercises and supplementary material for the machine learning operations course at DTU.

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

This repository contains small projects related to Neural Networks and Deep Learning in general. Subjects are closely linekd with articles I publish on Medium. I encourage you both to read as well as to check how the code works in the action.

Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models

PyTorch implementation for 3D Bounding Box Estimation Using Deep Learning and Geometry

Two-stage deep learning pipeline: YOLOv5 face detection plus a CNN (ResNet-18 / InceptionResNetV1) for age-group and gender prediction on images, video, and webcam.