Hybrid Imaging and Visualization - Awange, Joseph; Paláncz, Béla; Völgyesi, Lajos; - Prospero Internet Bookshop

Hybrid Imaging and Visualization: Employing Machine Learning with Mathematica - Python
 
Product details:

ISBN13:9783031728167
ISBN10:3031728165
Binding:Hardback
No. of pages:344 pages
Size:235x155 mm
Language:English
Illustrations: 73 Illustrations, black & white; 481 Illustrations, color
700
Category:

Hybrid Imaging and Visualization

Employing Machine Learning with Mathematica - Python
 
Edition number: Second Edition 2024
Publisher: Springer
Date of Publication:
Number of Volumes: 1 pieces, Book
 
Normal price:

Publisher's listprice:
EUR 213.99
Estimated price in HUF:
93 021 HUF (88 591 HUF + 5% VAT)
Why estimated?
 
Your price:

74 416 (70 873 HUF + 5% VAT )
discount is: 20% (approx 18 604 HUF off)
Discount is valid until: 31 December 2024
The discount is only available for 'Alert of Favourite Topics' newsletter recipients.
Click here to subscribe.
 
Availability:

Not yet published.
 
  Piece(s)

 
Short description:

This second edition of the book that targets those in computer algebra and artificial intelligence introduces Black Hole algorithm that is essential for optimizing hyperparameters, an important task in machine learning where mostly, stochastic global methods are used as well as ChatGPT, a novel and in the last few years, very popular Generative AI technology. In addition, fisher discriminant, a linear discriminant that can provide an optimal separation of objects, and the conversion of time series into images thereby making it possible to employ convolution neural network to classify time series effectively are presented.

Long description:

This second edition of the book that targets those in computer algebra and artificial intelligence introduces Black Hole algorithm that is essential for optimizing hyperparameters, an important task in machine learning where mostly, stochastic global methods are used as well as ChatGPT, a novel and in the last few years, very popular Generative AI technology. In addition, fisher discriminant, a linear discriminant that can provide an optimal separation of objects, and the conversion of time series into images thereby making it possible to employ convolution neural network to classify time series effectively are presented.

Table of Contents:

Chapter 1. Dimension Reduction.- Chapter 2. Classification.- Chapter 3. Clustering.- Chapter 4. Regression.- Chapter 5. Neural Networks.- Chapter 6. Optimizing Hyperparameters.- Chapter 7. ChatGPT.