首发于Learning Algorithms
DS/ML/DL学习指北

DS/ML/DL学习指北

按：本文最初发布于我的个人网站random walk。（由于专注于知乎，以及个人的研究和时间关系，个人网站已于2018年停更。近期会抽一些时间，将其中的一些内容搬到知乎上来，除了保证阅读的流畅，内容基本不做更新（比如框架方面，这两年已经有了很大改进与进展，除了TensorFlow2.0外，还有华为MindSpore，清华jittor，旷视MegEngine，一流科技OneFlow等；应用方面，这两年出现了很多AI+X的科学应用，比如PINN, CFDNet, AlphaFold, DeePMD等），对于有些领域的新进展，有机会我会在一些专栏里专文介绍，希望上面的一些知识（有些或许已经过时）还能对大家起一点点帮助作用。）

预备知识

  • 微积分⭐️
  • 概率统计⭐️⭐️⭐️⭐️
  • 线性代数⭐️⭐️⭐️⭐️
  • 矩阵论⭐️⭐️
  • 优化⭐️⭐️⭐️⭐️
  • 运筹学
  • 泛函分析／实分析／复分析
  • 微分几何／代数几何／热带几何
  • 流形／群论
  • 测度论
  • 信息论

书籍

  • Eric Lehman, F Thomson Leighton and Albert R Meyer, Mathematics for Computer Science
  • Gilbert Strang, Linear Algebra⭐️⭐️⭐️⭐️
  • E. T. Jaynes, Probability Theory: The Logic of Science
  • Larry Wasserman, All of Statistics⭐️⭐️⭐️
  • Trevor Hastie, Robert Tibshirani and Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction⭐️⭐️⭐️
  • Jiawei Han, Micheline Kamber and Jian Pei, Data Mining: Concepts and Techniques⭐️⭐️⭐️⭐️
  • Christopher D. Manning, Prabhakar Raghavan and Hinrich Schutze, Introduction to Information Retrieval⭐️⭐️⭐️⭐️
  • Avrim Blum, John Hopcroft and Ravindran Kannan, Foundations of Data Science⭐️⭐️⭐️⭐️
  • Joel Grus, Data Science from Scratch First Principles with Python
  • Anshul Joshi, Julia for Data Science
  • Rachel Schutt and Cathy O’Neil, Doing Data Science
  • Sebastian Gutierrez, Data Scientists at Work[That chapter written by Yann LeCun, especially]
  • Amy N. langville and Carl D. Meyer, Google's PageRank and Beyond
  • Stuart J. Russell and Peter Norvig, Artificial Intelligence: A Modern Approach⭐️⭐️
  • Tom M. Mitchell, Machine Learning⭐️⭐️⭐️
  • Christopher Bishop, Pattern Recognition and Machine Learning⭐️⭐️⭐️
  • Kevin P. Murphy, Machine Learning: A Probabilistic Perspective⭐️⭐️⭐️⭐️
  • Daphne Koller and Nir Friedman, Probalistic graphical Models: Principles and Techniques⭐️⭐️⭐️⭐️
  • 周志华, 机器学习[西瓜书]⭐️⭐️⭐️
  • 周志华, Ensemble Methods
  • 李航, 统计机器学习⭐️⭐️⭐️
  • Peter Harrington, Machine Learning in Action[中文版: 机器学习实战]⭐️⭐️⭐️
  • Bradley Efron and Robert J. Tibshirani, An Introduction to the Bootstrap
  • Stephen Boyd and Lieven Vandenberghe, Convex Optimization⭐️⭐️⭐️⭐️：优化领域的必读经典
  • Michael Nielsen, Neural Networks and Deep Learning⭐️⭐️
  • Li Deng and Dong Yu, Deep Learning: Methods and Applications
  • Dong Yu and Li Deng, Automatic Speech Recognition: A Deep Learning Approach
  • Li Deng and Dong Yu, Deep Learning For Signal And Information Processing
  • Romain Couillet and Merouane Debbah, Random Matrix Methods for Wireless Communications
  • Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning⭐️⭐️⭐️⭐️⭐️：DL领域三代顶尖学者联合打造，包含basics, background, ML, optimization, regularization, practice, CNN(conv+pooling), RNN(LSTM/GRU), more research parts，内容层次适合各类研究兴趣
  • Nikhil Ketkar, Deep Learning with Python⭐️⭐️:图文并茂，通俗易懂，很适合入门
  • Francois Chollet, Deep Learning with Python⭐️⭐️⭐️:Keras开发者最新力作

实用教程

Python

数据科学

机器学习

神经网络

深度学习

博客汇总

视频课程

MOOC

会议&期刊

  • AAAI
  • ACL
  • ACM
  • AISTATS
  • COLT
  • CVPR
  • ECCV
  • ECML
  • EMNLP
  • ICASSP
  • ICCV
  • ICDE
  • ICLR
  • ICML
  • IEEE
  • IJCAI
  • IJCV
  • JMLR
  • KDD
  • Neural Computation
  • Neural Networks
  • NIPS
  • TPAMI
  • PyCon
  • SciPy
  • SIAM
  • SIGGRAPH
  • Strata
  • UAI

数据集

模型

  • LeNet
  • AlexNet⭐️⭐️⭐️
  • ZFNet
  • GoogLeNet
  • VGGNet
  • ResNet⭐️⭐️
  • WaveNet

框架

  • Theano(LISA Lab)
  • Caffe
  • Caffe2(Facebook)
  • TensorFlow(Google)
  • Keras
  • Lasagne
  • MXNet(Amazon)
  • MLlib: Spark
  • DL4J: Java
  • NLTK(Microsoft)
  • Torch: Lua
  • PyTorch
  • Chainer
  • PaddlePaddle(Baidu): Docker+Python/C++
  • H2O
  • Mocha: Julia

实例

发布于 2021-04-09 17:48
机器学习
深度学习（Deep Learning）
数据科学

文章被以下专栏收录