-Artificial Intelligent: A Modern approach, Stuart Russell and Peter Norvig
A comprehensive book on AI, covers almost everything, the fundamentals of logic reasoning, inference, classical approaches, as well as modern subjects such as NLP, computer vision, and robotics
Pattern Recognition and Machine Learning, Chris Bishop
A book with self-contained introduction about regression, classification, kernel methods, graphical model, state-space models, with much focus on probabilistic model. Very suitable for introductory book.
Machine Learning: A probabilistic perspective, Kevin Murphy
A comprehensive book about machine learning with probabilistic models, and inference.
Elements of Statistical Learning, Trevor Hastie, Robert Tibshirani, Jerome Friedman
A more advanced book, with focus on statistical optimization, and theory.
机器学习(周志华)
统计机器学习(李航)
Classical papers:
Natural language processing (almost) from scratch,
a must read paper about (shallow) semantic parsing using end-to-end deep learning models.
Sequence to sequence learning, NIPS 2014, Ilya Sutskever, Oriol Vinyals, Quoc Le
a must read paper about sequence learning, the foundation of all modern machine translation and language generation work.
Neural machine translation by jointly learning to align and translate, Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio
a must read paper about how to use attention in sequence to sequence framework. Attention is the basic technique in RNN models.
Learning Deep Structured Semantic Models for Web Search using Clickthrough Data, Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, Larry Heck
a foundational work on neural network based similarity matching technique. Very useful for information retrieval and ranking tasks.
Machine Learning and AI
-Artificial Intelligent: A Modern approach, Stuart Russell and Peter Norvig A comprehensive book on AI, covers almost everything, the fundamentals of logic reasoning, inference, classical approaches, as well as modern subjects such as NLP, computer vision, and robotics
Elements of Statistical Learning, Trevor Hastie, Robert Tibshirani, Jerome Friedman A more advanced book, with focus on statistical optimization, and theory.
Classical papers: