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

MultiLayer Perceptron

When we connect the artificial neurons together, based on a well-defined structure, we call it a neural network. Here is the simplest neural network with one neuron:

Neural network with one neuron

We connect the neurons such that the output of one layer becomes the input of the next layer, until the final layer's output becomes the final output. Such neural networks are called feed forward neural networks (FFNN). As these FFNNs are made up of layers of neurons connected together, they are hence called MultiLayerPerceptrons (MLP) or deep neural networks (DNN).

As an example, the MLP depicted in the following diagram has three features as inputs: two hidden layers of five neurons each and one output y. The neurons are fully connected to the neurons of the next layer. Such layers are also called dense layers or affine layers and such models are also known as sequential models.

Let's revisit some of the example datasets that we explored earlier and build simple neural networks...