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
Contributors
Preface
19
Tensor Processing Units
Index

Chapter 11. RNN with TensorFlow and Keras

In problems involving ordered sequences of data, such as time series Forecasting and natural language processing, the context is very valuable to predict the output. The context for such problems can be determined by ingesting the whole sequence, not just one last data point. Thus, the previous output becomes part of the current input, and when repeated, the last output turns out to be the results of all the previous inputs along with the last input. Recurrent Neural Network (RNN) architecture is a solution for handling  machine learning problems that involve sequences.

Recurrent Neural Network (RNN) is a specialized neural network architecture for handling sequential data. The sequential data could be the sequence of observations over a period of time, as in time series data, or sequence of characters, words, and sentences, as in textual data.

One of the assumptions for the standard neural network is that the input data is arranged in a way that one...