The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

目标是提供一个完整的Java机器学习(Machine Learning/ML)框架,作为人工智能在学术界与工业界的桥梁. 让相关领域的研发人员能够在各种软硬件环境/数据结构/算法/模型之间无缝切换. 涵盖了从数据处理到模型的训练与评估各个环节,支持硬件加速和并行计算,是最快最全的Java机器学习库.

基于Apache Spark的Netflix电影的离线与实时推荐系统

TensorFlow implementation of an arbitrary order Factorization Machine

专注于解决推荐领域与搜索领域的两个核心问题:排序预测(Ranking)和评分预测(Rating). 为相关领域的研发人员提供完整的通用设计与参考实现. 涵盖了70多种排序预测与评分预测算法,是最快最全的Java推荐与搜索引擎.

AI Challenger, a platform for open datasets and programming competitions to artificial intelligence (AI) talents around the world.

Convolutional Neural Network for Text Classification in Tensorflow