This specific ISBN edition is currently not available.View all copies of this ISBN edition:
A smart computer looking at popular human images At the 2014 International Conference on Machine Learning, a team from the University of Toronto’s Deep Learning Group presented a paper titled Multimodal Neural Language Models, which describes a method for training a neural network to generate natural language text descriptions from images. As a supplement to this paper, they released both sample code and a working demonstration. Machine learning is a set of techniques in computer science involving algorithms that can ‘learn’—that is, which modify themselves in response to data—and can make predictions when exposed to new data, informed by that learning. The contents of this book are the result of exposing the Toronto team’s model to a body of work it had not seen before—breaking news photographs, taken at random from Reuters. Published as a Workbook by Modes Vu.
"synopsis" may belong to another edition of this title.
Book Description Modes Vu, 2015. Paperback. Condition: Brand New. 52 pages. 6.00x4.50x0.13 inches. In Stock. Seller Inventory # zk9187829312