Deep Learning in Neural Networks: An Overview (Juergen Schmidhuber)

0.0 (0)
Deep Learning in Neural Networks: An Overview (Juergen Schmidhuber)

Deep artificial neural networks, especially recurrent ones, have recently taken first place in many machine learning and pattern recognition competitions. This historical study provides a succinct summary of pertinent works, many of which date back to the previous millennium.

The complexity of credit assignment paths—chains of potentially understandable causal linkages between actions and effects—distinguishes shallow and deep learners. It reviews unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and massive networks, as well as deep supervised learning (including recapitulating the history of backpropagation).

The invited Deep Learning (DL) overview's preprint is available here. Giving thanks to individuals who made contributions to the current state of the art is one of its objectives. It admits that striving to accomplish this goal has its limitations. The DL research community itself can be seen as a dynamic, deep network of researchers who have affected one another in a variety of intricate ways. It attempted, beginning with current DL results, to track the history of pertinent concepts going back fifty years and beyond, occasionally utilizing "local search" to follow the citations of citations backward in time. Additional global search techniques were used, helped by interviewing multiple neural network specialists, because not all DL publications correctly mention earlier pertinent work. As a result, the present preprint mostly consists of references.

Ebook Details

About the Authors
Computer scientist Juergen Schmidhuber is well known for his contributions to artificial intelligence, deep learning, and artificial neural networks.
Published Date / Year
(October 2014) and University of Lugano
Non-exclusive License to Distribute
eBook Format
PDF (206 pages)

Similar Programming & Computer Books

Handbook of Digital Face Manipulation and Detection: From DeepFakes to Morphing Attacks (Christian Rathgeb, et al)
The first thorough compilation of research on the popular subject of digital face alteration, including DeepFakes, Face Morphing, and Reenactment, is offered in this open access book. ...
Prolog and Natural-Language Analysis (Fernando Pereira, et al)
This free programming book offers an accessible and useful introduction to logic programming and the logic-programming language Prolog, which may be used to create the fundamental elements of natural...
NLP - Skills for Learning (Peter Freeth)
This free programming book explores how NLP (Neuro Linguistic Programming) is used in training, education, and instruction. It serves as both an introduction to NLP and a book about...
Natural Language Processing with Python – Analyzing Text with the Natural Language Toolkit (Steven Bird, et al)
The Natural Language Toolkit (NLTK) book is updated for Python 3 and NLTK 3 in this online edition from 2015.  
Biomimetics: Learning from Nature (Amitava Mukherjee)
This free programming book introduces us to the fascinating field of biomimetics and explores the numerous fields in which it is used. The 25 chapters in this book provide...
Systems and Computational Biology - Bioinformatics and Computational Modeling (Ning-Sun Yang)
In this free programming book, we examine cutting-edge scientific and technological methods for promoting human health, producing food and animal feed, and safeguarding the environment. ...
Planning for Big Data: A CIO's Handbook to the Changing Data Landscape (Edd Dumbill)
This free programming book offers a useful, approachable "brief" on the state of Big Data analytics today and how you may profitably use this technology to boost your company's...
Big Data Now: Current Perspectives from O'Reilly Radar (O'Reilly Radar Team)
This free programming book summarizes the report's findings on trends, techniques, applications, and predictions.  
Mind, Body, World: Foundations of Cognitive Science (Michael R.W. Dawson)
This book answers several problems that individuals working in the field of cognitive science are now asking and is designed to expose graduate and senior undergraduate students to the...
Brain, Vision and AI (Cesare Rossi)
This book's objective is to present fresh perspectives, original findings, and real-world examples related to service robotics.  

Others Programming Books by

Basic Data Analysis and More - A Guided Tour Using python (Oliver Melchert)
A number of often-used statistical techniques will be described and shown in these lecture notes. They enable the post-processing of data resulting from, for instance, extensive numerical simulations (aka...
High Performance Computing and Numerical Modelling (Volker Springel)
This book offers a detailed explanation of numerical methods used in engineering modeling. In order to reinforce for students that numerical methods are a collection of mathematical modeling tools...
Foundations of Descriptive and Inferential Statistics (Henk van Elst)
These lecture notes were created with the intention of giving undergraduate and graduate students, particularly those studying social sciences, economics, and financial services, an approachable but technically sound introduction...
Deep Learning: Technical Introduction (Thomas Epelbaum)
The three most popular types of neural network architectures—Feedforward, Convolutional, and Recurrent—are presented in this book in a technical but hopefully instructive manner.
A Brief Introduction to Machine Learning for Engineers (Osvaldo Simeone)
Statistical learning theory, probabilistic graphical models, supervised and unsupervised learning, and approximation inference are just a few of the fundamental ideas, algorithms, and theoretical frameworks that this book seeks...

User reviews

There are no user reviews for this listing.
Rate this Book