Introduction to Machine LearningMachine learning is one of the fastest growing areas of computer science, with far-reaching applications. The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way. The book provides an extensive theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations that transform these principles into practical algorithms. Following a presentation of the basics of the field, the book covers a wide array of central topics that have not been addressed by previous textbooks. These include a discussion of the computational complexity of learning and the concepts of convexity and stability; important algorithmic paradigms including stochastic gradient descent, neural networks, and structured output learning; and emerging theoretical concepts such as the PAC-Bayes approach and compression-based bounds. Designed for an advanced undergraduate or beginning graduate course, the text makes the fundamentals and algorithms of machine learning accessible to students and nonexpert readers in statistics, computer science, mathematics, and engineering. |
Contents
| 1 | |
| 5 | |
Machine Learning Traditional AI 912 | 9 |
Machine Learning Categories 1319 | 13 |
Machine Learning Supervised 2026 | 20 |
Machine Learning Unsupervised 2728 | 27 |
Machine Learning Artificial Neural Networks 2942 | 29 |
TensorFlow Introduction 4348 | 43 |
Understanding Artificial Intelligence 49139 | 49 |
Common terms and phrases
accuracy amount of data array Artificial Intelligence Artificial Neural Networks batch batch_size batch_x chapter classification cluster computer science Consider the following Convolutional Neural Networks creating data mining data points data set decision trees deep learning deep neural networks defined diagram dtype Epoch feature feed_dict focus following output function Google graph hidden layer image recognition implementation import matplotlib.pyplot import tensorflow includes input data Instructions for updating iterations labels learning and deep Learning Machine learning linear regression logistic regression machine learning algorithms mathematical matplotlib.pyplot as plt matrix mnist Natural language processing necessary modules neurons nodes np import numpy as np parameters plt.show predict problems programs Python recurrent neural network Reinforcement Learning single layer perceptron softmax specific speech recognition statistical techniques Step Stochastic Gradient descent supervised learning tensor tensorflow as tf tf.Session()as sess TFLearn training data understand unsupervised variables vector X_test y_batch y_train