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

The perceptron

Let's understand the most basic building block of a neural network, the perceptron, also known as the artificial neuron. The concept of the perceptron originated in the works of Frank Rosenblatt in 1962.


You may want to read the following work to explore the origins of neural networks:


Frank Rosenblatt, Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Spartan Books, 1962

In the most simplified view, a perceptron is modeled after the biological neurons such that it takes one or multiple inputs and combines them to generate output.

As shown in the following image, the perceptron takes three inputs and adds them to generate output y:

 Simple perceptron

This perceptron is too simple to be of any practical use. Hence, it has been enhanced by adding the concept of weights, bias, and activation function. The weights are added to each input to get the weighted sum. If the weighted sum

  is less than the threshold value, then the output is 0, else output...