Book Image

Artificial Intelligence with Python - Second Edition

By : Prateek Joshi
Book Image

Artificial Intelligence with Python - Second Edition

By: Prateek Joshi

Overview of this book

Artificial Intelligence with Python, Second Edition is an updated and expanded version of the bestselling guide to artificial intelligence using the latest version of Python 3.x. Not only does it provide you an introduction to artificial intelligence, this new edition goes further by giving you the tools you need to explore the amazing world of intelligent apps and create your own applications. This edition also includes seven new chapters on more advanced concepts of Artificial Intelligence, including fundamental use cases of AI; machine learning data pipelines; feature selection and feature engineering; AI on the cloud; the basics of chatbots; RNNs and DL models; and AI and Big Data. Finally, this new edition explores various real-world scenarios and teaches you how to apply relevant AI algorithms to a wide swath of problems, starting with the most basic AI concepts and progressively building from there to solve more difficult challenges so that by the end, you will have gained a solid understanding of, and when best to use, these many artificial intelligence techniques.
Table of Contents (26 chapters)
Other Books You May Enjoy

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...