RISS 검색 - 단행본 상세보기

부가정보

목차 (Table of Contents)

자료제공 :
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.

자료제공 :
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.

온라인 도서 정보

온라인 서점 구매

온라인 서점 구매 정보
서점명	서명	판매현황	종이책			전자책 구매링크
서점명	서명	판매현황	정가	판매가(할인율)	포인트(포인트몰)	전자책 구매링크
	Deep Learning Architectures: A Mathematical Approach (Hardcover, 2020)	판매중	167,600원	137,430원 (18%)	6,880포인트
	Deep Learning Architectures: A Mathematical Approach	판매중	193,850원	174,460원 (10%)	8,730포인트 (5%)

포인트 적립은 해당 온라인 서점 회원인 경우만 해당됩니다.
상기 할인율 및 적립포인트는 온라인 서점에서 제공하는 정보와 일치하지 않을 수 있습니다.
RISS 서비스에서는 해당 온라인 서점에서 구매한 상품에 대하여 보증하거나 별도의 책임을 지지 않습니다.

책소개

자료제공 :

Deep Learning Architectures: A Mathematical Approach (A Mathematical Approach)

This book describes how neural networks operate from the mathematical point of view. As a result, neural networks can be interpreted both as function universal approximators and information processors. The book bridges the gap between ideas and concepts of neural networks, which are used nowadays at an intuitive level, and the precise modern mathematical language, presenting the best practices of the former and enjoying the robustness and elegance of the latter. This book can be used in a graduate course in deep learning, with the first few parts being accessible to senior undergraduates. In addition, the book will be of wide interest to machine learning researchers who are interested in a theoretical understanding of the subject.