Your Waterstones card is changing, introducing...
TELL ME MORE
Perturbations, Optimization, and Statistics - Neural Information Processing series (Hardback)
  • Perturbations, Optimization, and Statistics - Neural Information Processing series (Hardback)
zoom

Perturbations, Optimization, and Statistics - Neural Information Processing series (Hardback)

(editor), (editor), (editor)
£47.00
Hardback 412 Pages / Published: 23/12/2016
  • We can order this

Usually despatched within 1 week

  • This item has been added to your basket
A description of perturbation-based methods developed in machine learning to augment novel optimization methods with strong statistical guarantees. In nearly all machine learning, decisions must be made given current knowledge. Surprisingly, making what is believed to be the best decision is not always the best strategy, even when learning in a supervised learning setting. An emerging body of work on learning under different rules applies perturbations to decision and learning procedures. These methods provide simple and highly efficient learning rules with improved theoretical guarantees. This book describes perturbation-based methods developed in machine learning to augment novel optimization methods with strong statistical guarantees, offering readers a state-of-the-art overview. Chapters address recent modeling ideas that have arisen within the perturbations framework, including Perturb & MAP, herding, and the use of neural networks to map generic noise to distribution over highly structured data. They describe new learning procedures for perturbation models, including an improved EM algorithm and a learning algorithm that aims to match moments of model samples to moments of data. They discuss understanding the relation of perturbation models to their traditional counterparts, with one chapter showing that the perturbations viewpoint can lead to new algorithms in the traditional setting. And they consider perturbation-based regularization in neural networks, offering a more complete understanding of dropout and studying perturbations in the context of deep neural networks.

Publisher: MIT Press Ltd
ISBN: 9780262035644
Number of pages: 412
Weight: 1021 g
Dimensions: 254 x 203 x 24 mm

You may also be interested in...

Superintelligence
Added to basket
£18.99
Hardback
Thoughtful Machine Learning
Added to basket
Bayesian Reasoning and Machine Learning
Added to basket
Introduction to Machine Learning
Added to basket
Reinforcement Learning
Added to basket
Understanding Machine Learning
Added to basket
Machine Learning
Added to basket
£39.99
Paperback
Web Data Mining
Added to basket
£54.99
Hardback
Machine Learning
Added to basket
Machine Learning
Added to basket
£42.50
Paperback
Machine Learning for Hackers
Added to basket
The Elements of Statistical Learning
Added to basket
Machine Learning
Added to basket
£52.99
Mixed media product

Reviews

Please sign in to write a review

Your review has been submitted successfully.