AI

MIT How to AI(Almost) Everything 前言 本门课程主要讲的是多模态大模型，而不是AI应用方式。 课程资料链接 Course Description Artificial Intelligence (AI) holds great promise as a technology to enhance digital productivity, physical interactions, overall well-being, and the human experience. To enable the true impact of AI, these systems will need to be grounded in real-world data modalities, from language-only systems to vision, audio, sensors, medical data, music, art, smell, and taste. This course will introduce the basic principles of AI (focusing on modern deep learning and foundation models) and how we can apply AI to novel real-world data modalities. In addition, we will introduce the principles of multimodal AI that can process many modalities at once, such as connecting language and multimedia, music and art, sensing and actuation, and more. ...

Knowledge Graphs for RAG Preface This article is a study note for the course https://www.deeplearning.ai/short-courses/knowledge-graphs-rag/. What you’ll learn in this course Knowledge graphs are used in development to structure complex data relationships, drive intelligent search functionality, and build powerful AI applications that can reason over different data types. Knowledge graphs can connect data from both structured and unstructured sources (databases, documents, etc.), providing an intuitive and flexible way to model complex, real-world scenarios. ...

前言 这是我对三周“超级兴趣课程”的一个总结。坦白说，只有当我不是真正学生物专业的时候，才不会觉得生物是个“天坑”——毕竟它是个劳动密集型学科。 我对各种新技术一直很感兴趣，生物信息学和基因测序自然也不例外。 ...

前言 虽然我平时最常用的是字节跳动出品的Trae，但在某种意义上，我也是最早使用Cursor的用户之一。 待我有空的时候，就打算开发一个基于Trae的Custom Agents Rules Generator，模拟类似的AI编程体验。 ...