You're reading from Artificial Intelligence with Python Your complete guide to building intelligent apps using Python 3.x

Product type Paperback

Published in Jan 2020

Publisher Packt

ISBN-13 9781839219535

Length 618 pages

Edition 2nd Edition

Languages

Python

Tools

TensorFlow

Concepts

Artificial Intelligence

Authors (2):

Prateek Joshi

Alberto Artasanchez

View More author details

Table of Contents (26) Chapters

Preface

1. Introduction to Artificial Intelligence

2. Fundamental Use Cases for Artificial Intelligence FREE CHAPTER

3. Machine Learning Pipelines

4. Feature Selection and Feature Engineering

5. Classification and Regression Using Supervised Learning

6. Predictive Analytics with Ensemble Learning

7. Detecting Patterns with Unsupervised Learning

8. Building Recommender Systems

9. Logic Programming

10. Heuristic Search Techniques

11. Genetic Algorithms and Genetic Programming

12. Artificial Intelligence on the Cloud

13. Building Games with Artificial Intelligence

14. Building a Speech Recognizer

15. Natural Language Processing

16. Chatbots

17. Sequential Data and Time Series Analysis

18. Image Recognition

19. Neural Networks

20. Deep Learning with Convolutional Neural Networks

21. Recurrent Neural Networks and Other Deep Learning Models

22. Creating Intelligent Agents with Reinforcement Learning

23. Artificial Intelligence and Big Data

24. Other Books You May Enjoy

25. Index

Identifying alphabet sequences with Conditional Random Fields

Conditional Random Fields (CRFs) are probabilistic models that are frequently used to analyze structured data. We use them to label and segment sequential data in various forms. Following are some of the most common use cases where CRFs are applied:

Handwriting recognition
Character recognition
Object detection
Named entity recognition
Gene prediction
Image segmentation
Part of speech tagging
Noise reduction

One item of note regarding CRFs is that they are discriminative models. Contrast this with HMMs, which are generative models.

We can define a conditional probability distribution over a labeled sequence of measurements. We will use this to build a CRF model. In HMMs, we define a joint distribution over the observation sequence and the labels.

One of the main advantages of CRFs is that they are conditional by nature. This is not the case with HMMs. CRFs do not assume...