Introduction to Cognitive Computing: A Guide for Individuals and Small Organizations

English | 28 Mar. 2017 | ASIN: B06XXR1QG6 | 137 Pages | PDF | 1.4 MB

This short book provides both an introduction to Cognitive Computing and practical examples that take the reader on a deeper dive into machine learning, deep neural networks using Google's TensorFlow library, and natural language processing.

Most of the book examples use Python, with a few in Java and TypeScript.

The book starts by reviewing Philosophy (study of Ontology's and Knowledge Representation), an overview of general Artificial Intelligence, Linguistics (understanding language will help us better extract useful information from English language text), and Neuroscience (to better understand how our minds work).

The home page for the resources for this book are both the author's web site www.markwatson.com and the github repository https://github.com/mark-watson/cognitive-computing-book

There are three parts to this book:

Part I - A Dive into Human Cognition and Cognitive Science

This section of the book will ground you in the science that forms the foundation of Cognition Technology with chapters on Philosophy (especially how it pertains to Knowledge Management and Knowledge Representation), Linguistics, general AI, and Neuroscience.

Part II - Using Machine Learning and Deep Learning Neural Networks to Model Cognition

We use Deep Learning Neural Networks for classification, logistic regression, Knowledge Representation, and Natural Language Processing. We start with some simple standalone programs (written in TypeScript, with JavaScipt versions also included) and then use Google's Tensorflow machine learning library for more complex examples. Tensorflow runs well for moderate size problems on your laptop and scales up using Google's Cloud Platform (or your own servers with GPU support). Currently deep learning networks are the most interesting and useful technology for modeling cognition. The author's primary personal interests in deep learning are NLP and language models.

Part III - Natural Language Processing and Knowledge Representation

Here we will dive deeper into practical applications of Natural Language Processing.