Book Image

Mastering Machine Learning Algorithms

Book Image

Mastering Machine Learning Algorithms

Overview of this book

Machine learning is a subset of AI that aims to make modern-day computer systems smarter and more intelligent. The real power of machine learning resides in its algorithms, which make even the most difficult things capable of being handled by machines. However, with the advancement in the technology and requirements of data, machines will have to be smarter than they are today to meet the overwhelming data needs; mastering these algorithms and using them optimally is the need of the hour. Mastering Machine Learning Algorithms is your complete guide to quickly getting to grips with popular machine learning algorithms. You will be introduced to the most widely used algorithms in supervised, unsupervised, and semi-supervised machine learning, and will learn how to use them in the best possible manner. Ranging from Bayesian models to the MCMC algorithm to Hidden Markov models, this book will teach you how to extract features from your dataset and perform dimensionality reduction by making use of Python-based libraries such as scikit-learn v0.19.1. You will also learn how to use Keras and TensorFlow 1.x to train effective neural networks. If you are looking for a single resource to study, implement, and solve end-to-end machine learning problems and use-cases, this is the book you need.
Table of Contents (22 chapters)
Title Page
Dedication
Packt Upsell
Contributors
Preface
13
Deep Belief Networks
Index

Addendum to HMMs


In the previous chapter, we discussed how it's possible to train a HMM using the forward-backward algorithm and we have seen that it is a particular application of the EM algorithm. The reader can now understand the internal dynamic in terms of E and M steps. In fact, the procedure starts with randomly initialized A and B matrices and proceeds in an alternating manner:

  • E-Step:
    • The estimation of the probability αtij that the HMM is in the state i at time t and in the state j at time t+1 given the observations and the current parameter estimations (A and B)
    • The estimation of the probability βti that the HMM is in the state i at time t given the observations and the current parameter estimations (A and B)
  • M-Step:
    • Computing the new estimation for the transition probabilities aij (A) and for the emission probabilities bip (B)

The procedure is repeated until the convergence is reached. Even if there's no explicit definition of a Q function, the E-step determines a split expression...