Book Image

Python: Advanced Guide to Artificial Intelligence

By : Giuseppe Bonaccorso, Rajalingappaa Shanmugamani
Book Image

Python: Advanced Guide to Artificial Intelligence

By: Giuseppe Bonaccorso, Rajalingappaa Shanmugamani

Overview of this book

This Learning Path is your complete guide to quickly getting to grips with popular machine learning algorithms. You'll be introduced to the most widely used algorithms in supervised, unsupervised, and semi-supervised machine learning, and learn how to use them in the best possible manner. Ranging from Bayesian models to the MCMC algorithm to Hidden Markov models, this Learning Path will teach you how to extract features from your dataset and perform dimensionality reduction by making use of Python-based libraries. You'll bring the use of TensorFlow and Keras to build deep learning models, using concepts such as transfer learning, generative adversarial networks, and deep reinforcement learning. Next, you'll learn the advanced features of TensorFlow1.x, such as distributed TensorFlow with TF clusters, deploy production models with TensorFlow Serving. You'll implement different techniques related to object classification, object detection, image segmentation, and more. By the end of this Learning Path, you'll have obtained in-depth knowledge of TensorFlow, making you the go-to person for solving artificial intelligence problems This Learning Path includes content from the following Packt products: • Mastering Machine Learning Algorithms by Giuseppe Bonaccorso • Mastering TensorFlow 1.x by Armando Fandango • Deep Learning for Computer Vision by Rajalingappaa Shanmugamani
Table of Contents (31 chapters)
Title Page
About Packt
Tensor Processing Units

Label propagation

Label propagation is a family of semi-supervised algorithms based on a graph representation of the dataset. In particular, if we have N labeled points (with bipolar labels +1 and -1) and M unlabeled points (denoted by y=0), it's possible to build an undirected graph based on a measure of geometric affinity among samples. If G = {V, E} is the formal definition of the graph, the set of vertices is made up of sample labels V = { -1, +1, 0 }, while the edge set is based on an affinity matrixW (often called adjacency matrix when the graph is unweighted), which depends only on the X values, not on the labels.

In the following graph, there's an example of such a structure:

Example of binary graph

In the preceding example graph, there are four labeled points (two with y=+1 and two with y=-1), and two unlabeled points (y=0). The affinity matrix is normally symmetric and square with dimensions equal to (N+M) x (N+M). It can be obtained with different approaches. The most common ones...