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

Application areas of RNNs


Some of the application areas where RNNs are used more often are as follows:

  • Natural Language Modeling: The RNN models have been used in natural language processing (NLP) for natural language understanding and natural language generation tasks. In NLP, an RNN model is given a sequence of words and it predicts another sequence of words. Thus, the trained models can be used for generating the sequence of words, a field known as Text Generation. For example, generating stories, and screenplays. Another area of NLP is language translation, where given a sequence of words in one language, the model predicts a sequence of words in another language.
  • Voice and Speech Recognition: The RNN models have great use in building models for learning from the audio data. In speech recognition, an RNN model is given audio data and it predicts a sequence of phonetic segments. It can be used to train the models to recognize the voice commands, or even for conversation with speech based...