Deep Learning Architectures: A Mathematical Approach

by Ovidiu Calin

Introductory Problems.- Activation Functions.- Cost Functions.- Finding Minima Algorithms.- Abstract Neurons.- Neural Networks.- Approximation Theorems.- Learning with One-dimensional Inputs.- Universal Approximators.- Exact Learning.- Information Representation.- Information Capacity Assessment.- Output Manifolds.- Neuromanifolds.- Pooling.- Convolutional Networks.- Recurrent Neural Networks.- Classification.- Generative Models.- Stochastic Networks.- Hints and Solutions.

Genres: Mathematics, Computer Science, Artificial Intelligence

792 pages, Paperback

Published February 17, 2020

Reviews

[Rarian Rakista · Rating 4 out of 5]

Was recommended this as a supplement to a Deep Learning course that was less rigorous than I'd like - the professor has insisted on teaching from handwritten notes, which is a nightmare. Proofs aplenty and not a lot of handholding, but if you've done discrete mathematics and real analysis you should be fine.

[Jessada Karnjana · Rating 5 out of 5]

ปัญหาหลักของเล่มนี้คือ typos เยอะมาก ถ้า proofreading ให้ดีกว่านี้ จะดีมาก ถ้าพิถีพิถันไม่ใช้ตัวแปรหลายความหมาย ก็จะดีมาก