The development of machine learning dates back to 1959 and has a rich history. The field is also evolving at an unprecedented rate. In a previous article , we discussed why the field of general artificial intelligence is about to explode. For those who are interested in getting into ML, don't delay, the time doesn't wait for me!
As I begin preparing for my PhD program this fall, I've curated some great web resources on machine learning and NLP. Usually I will find an interesting tutorial or video, and then I will find three or four, or even more tutorials or videos. Looking back, I found that there are 20 more resources in the standard favorites for me to learn (Tab Bundler, a tool for improving efficiency is recommended).
After finding over 25 "cheat sheets" about ML, I wrote a blog post with hyperlinks to the resources.
To help children's shoes who are going through a similar exploration process, I've put together a list of the best tutorials I've found so far. Of course this isn't the most comprehensive collection of ML on the web, and some of it is pretty generic. My goal is to find the best tutorials on machine learning sub-directions and NLP.
I cite the basics for a succinct introduction to the concept. I've avoided chapters that contain tomes, and scientific papers that don't help understanding the concepts. So why not buy a book? Because tutorials can better help you learn a skill or open up new horizons.
I divided this blog post into four parts, Machine Learning, NLP, Python, and Mathematical Fundamentals . In each subsection I will randomly introduce some questions. Due to the abundance of learning materials in this area, this article does not cover everything.
machine learning
1. Machine learning is so much fun! (medium.com/@ageitgey)
Machine Learning Crash Course (ML by Berkeley):
Part I:https://ml.berkeley.edu/blog/2016/11/06/tutorial-1/
Part II:https://ml.berkeley.edu/blog/2016/12/24/tutorial-2/
Part III:https://ml.berkeley.edu/blog/2017/02/04/tutorial-3/
Introduction and Application of Machine Learning: Example Illustrations (toptal.com)
A Simple Guide to Machine Learning (monkeylearn.com)
How to choose a machine learning algorithm? (sas.com)
2、Activation and Loss Functions
Activation function and loss function
sigmoid neurons (neuralnetworksanddeeplearning.com)
What is the role of activation function in neural network? (quora.com)
Activation function of neural network and its advantages and disadvantages (stats.stackexchange.com)
Activation functions and their classification comparison (medium.com)
Understanding Log Loss (exegetic.biz)
Loss function (Stanford CS231n)
Comparison of loss functions L1 and L2 (rishy.github.io)
Cross-entropy loss function (neuralnetworksanddeeplearning.com)
3. Bias
The role of bias in neural networks (stackoverflow.com)
Bias Nodes in Neural Networks (makeyourownneuralnetwork.blogspot.com)
What is Bias in Artificial Neural Networks (quora.com)
4. Perceptron
The Perceptron Model (neuralnetworksanddeeplearning.com)
One-layer neural network (perceptron model) (dcu.ie)
From perceptron models to deep networks (toptal.com)
5. Regression algorithm
Introduction to Linear Regression Analysis (duke.edu)
Linear Regression (ufldl.stanford.edu)
Linear Regression (readthedocs.io)
Logistic Regression (readthedocs.io)
Simple Linear Regression Tutorial for Machine Learning (machinelearningmastery.com)
Logistic Regression Tutorial for Machine Learning (machinelearningmastery.com)
softmax regression (ufldl.stanford.edu)
6. Gradient descent
Gradient Descent-Based Learning (neuralnetworksanddeeplearning.com)
Gradient Descent (iamtrask.github.io)
How to understand the gradient descent algorithm? (kdnuggets.com)
Overview of Gradient Descent Optimization Algorithms (sebastianruder.com)
Optimization Algorithm: Stochastic Gradient Descent Algorithm (Stanford CS231n)
7. Generative learning
Generative Learning Algorithms (Stanford CS229)
Example Analysis of Bayesian Classification Algorithms (monkeylearn.com)
8. Support Vector Machines
Getting Started with Support Vector Machines (SVM) (monkeylearn.com)
Support Vector Machines (Stanford CS229)
Linear Classification: Support Vector Machines, Softmax (Stanford 231n)
9. Backpropagation
Backpropagation Algorithms Must Know (medium.com/@karpathy)
Come, show me the neural network backpropagation algorithm? (github.com/rasbt)
How does the backpropagation algorithm work? (neuralnetworksanddeeplearning.com)
Backpropagation Algorithm and Gradient Vanishing along Time (wildml.com)
A Simple Primer for Backpropagation Algorithms in Edge Time (machinelearningmastery.com)
Go for a run, backpropagation algorithm! (Stanford CS231n)
10. Deep Learning
Deep Learning in a Nutshell (nikhilbuduma.com)
Deep Learning Tutorial (Quoc V. Le)
Deep learning, what the hell? (machinelearningmastery.com)
11. Optimization algorithm and dimensionality reduction algorithm
Seven Alchemy Techniques for Data Dimensionality Reduction (knime.org)
Principal Component Analysis (Stanford CS229)
Dropout: A Simple Way to Improve Neural Networks (Hinton @ NIPS 2012)
How to sneak your deep neural network at home? (rishy.github.io)
12. Long Short-Term Memory (LSTM)
Understanding LSTM Networks (colah.github.io)
Talking about the LSTM model (echen.me)
13. Convolutional Neural Networks (CNNs)
Getting Started with Convolutional Networks (neuralnetworksanddeeplearning.com)
Deep Learning and Convolutional Neural Network Models (medium.com/@ageitgey)
Dismantling the Convolutional Network Model (colah.github.io)
Understanding Convolutional Networks (colah.github.io)
14. Recurrent Neural Networks (RNNs)
Recurrent Neural Network Tutorial (wildml.com)
Attention Models and Augmented Recurrent Neural Networks (distill.pub)
Such an unscientific recurrent neural network model (karpathy.github.io)
In-depth Recurrent Neural Network Models (nikhilbuduma.com)
15. Reinforcement Learning
Reinforcement learning and its implementation guide for Xiaobai (analyticsvidhya.com)
Reinforcement Learning Tutorial (mst.edu)
Reinforcement learning, have you learned it? (wildml.com)
Deep Reinforcement Learning: Playing with Pong (karpathy.github.io)
16. Adversarial generative network models (GANs)
What is an adversarial generative network model? (nvidia.com)
Creating 8 Pixel Art with Adversarial Generative Networks (medium.com/@ageitgey)
Getting Started with Adversarial Generative Networks (TensorFlow) (aylien.com)
"Adversarial Generative Networks" (Grade 1~Volume 1) (oreilly.com)
17. Multi-task learning
Overview of Multi-Task Learning in Deep Neural Networks (sebastianruder.com)
NLP
1、NLP
"Natural Language Processing Based on Neural Network Model" (Grade 1~Volume 1) (Yoav Goldberg)
The Definitive Guide to Natural Language Processing (monkeylearn.com)
Introduction to Natural Language Processing (algorithmia.com)
Natural Language Processing Tutorial (vikparuchuri.com)
Natural Language Processing (almost) from Scratch (arxiv.org)
Courses for Middle and High School Students: Natural Language Processing (arxiv.org)
2. Deep Learning and NLP
Deep Learning-Based NLP Applications (arxiv.org)
NLP based on deep learning (Richard Socher)
Understanding Convolutional Neural Networks in NLP (wildml.com)
Deep Learning, NLP, Representation Learning (colah.github.io)
Understanding Neural Network-Based Natural Language Processing (Torch Implementation) (nvidia.com)
Deep Learning in NLP (Pytorch Implementation) (pytorich.org)
3. Word Vectors
Bag of words meets perceptron bagging (kaggle.com)
Learning Word Embedding Representations (sebastianruder.com)
Part I:http://sebastianruder.com/word-embeddings-1/index.html
Part II:http://sebastianruder.com/word-embeddings-softmax/index.html
Part III:http://sebastianruder.com/secret-word2vec/index.html
The Magical Power of Word Embedding Representations (acolyer.org)
Explaining parameter learning for word2vec (arxiv.org)
word2vec tutorial skip-gram model, negative sampling (mccormickml.com)
4、Encoder-Decoder
Application of Attention Mechanism and Memory Mechanism in Deep Learning and NLP (wildml.com)
Sequence-to-Sequence Models (tensorflow.org)
Learning Sequence-to-Sequence Models with Neural Networks (NIPS 2014)
Language translation based on deep learning and magic sequences (medium.com/@ageitgey)
Python
1、Python
Seven Steps to Mastering Machine Learning with Python (kdnuggets.com)
A brief example of machine learning (nbviewer.jupyter.org)
2. Examples
How Xiaobai implements the perceptron algorithm in python (machinelearningmastery.com)
Primary school students implement a neural network in python (wildml.com)
Implement a neural network algorithm in just 11 lines of python code (iamtrask.github.io)
Do-it-yourself implementation of the nearest neighbor algorithm with ptython (kdnuggets.com)
How to Learn Addition with seq2seq Recurrent Neural Networks (machinelearningmastery.com)
3. Scipy and numpy
Scipy Course Notes (scipy-lectures.org)
Python Numpy Tutorial (Stanford CS231n)
Getting Started with Numpy and Scipy (UCSB CHE210D)
Python Microcourses for Scientists (nbviewer.jupyter.org)
4、scikit-learn
Scik-learn tutorial at PyCon (nbviewer.jupyter.org)
Classification Algorithms in Scikit-learn (github.com/mmmayo13)
Scikit-learn Tutorial (scikit-learn.org)
Concise Scikit-learn tutorial (github.com/mmmayo13)
5、Tensorflow
Tensorflow Tutorial (tensorflow.org)
Getting Started with Tensorflow - CPU vs GPU
(medium.com/@erikhallstrm)
Getting Started with Tensorflow (metaflow.fr)
Tensorflow implements RNNs (wildml.com)
Tensorflow implements CNN model for text classification (wildml.com)
How to do text summarization with Tensorflow (surmenok.com)
6、PyTorch
Pytorch Tutorial (pytorch.org)
Getting Started with Pytorch (gaurav.im)
Deep Learning Tutorial with Pytorch (iamtrask.github.io)
Pytorch in action (github.com/jcjohnson)
PyTorch Tutorial (github.com/MorvanZhou)
PyTorch tutorial for deep learning researchers (github.com/yunjey)
math
1. Mathematics in Machine Learning (ucsc.edu)
https://people.ucsc.edu/~praman1/static/pub/math-for-ml.pdf
Mathematical Fundamentals of Machine Learning (UMIACS CMSC422)
2. Linear Algebra
A Concise Guide to Linear Algebra (betterexplained.com)
Matrix multiplication in the eyes of coders (betterexplained.com)
Understanding the cross product operation (betterexplained.com)
Understanding Dot Multiplication (betterexplained.com)
Linear Algebra in Machine Learning (U. of Buffalo CSE574)
Deep Learning Cheat Sheet (medium.com)
Review Linear Algebra with After-School Readings (Stanford CS229)
3. Probability Theory
Bayesian Theory (betterexplained.com)
Understanding Bayesian Probability Theory (Stanford CS229)
Review of Probability Theory in Machine Learning (Stanford CS229)
Probability Theory (U. of Buffalo CSE574)
Probability Theory in Machine Learning (U. of Toronto CSC411)
4. Calculus
How to Understand Derivatives: Derivative Laws, Exponents, and Algorithms (betterexplained.com)
How to Understand Derivatives, Multiplication, Exponents, Chaining (betterexplained.com)
Vector Computation, Understanding Gradients (betterexplained.com)
Differential Computing (Stanford CS224n)
Introduction to Computational Methods (readthedocs.io)
Re: https://www.leiphone.com/news/201801/pM48Ekleds2b6j5i.html