Klaus-Robert Müller

Sara A. Solla

Todd K. Leen

The annual conference on Neural Information Processing Systems (NIPS) is the flagship conference on neural computation. It draws preeminent academic researchers from around the world and is widely considered to be a showcase conference for new developments in network algorithms and architectures. The broad range of interdisciplinary research areas represented includes computer science, neuroscience, statistics, physics, cognitive science, and many branches of engineering, including signal processing and control theory. Only about 30 percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. These proceedings contain all of the papers that were presented.

Proceedings of the 1999 Conference

Advances in Neural Information Processing Systems 12

Kristof T. Schütt

Stefan Chmiela

O. Anatole von Lilienfeld

Alexandre Tkatchenko

Koji Tsuda

Designing molecules and materials with desired properties is an important prerequisite for advancing technology in our modern societies. This requires both the ability to calculate accurate microscopic properties, such as energies, forces and electrostatic multipoles of specific configurations, as well as efficient sampling of potential energy surfaces to obtain corresponding macroscopic properties. Tools that can provide this are accurate first-principles calculations rooted in quantum mechanics, and statistical mechanics, respectively. Unfortunately, they come at a high computational cost that prohibits calculations for large systems and long time-scales, thus presenting a severe bottleneck both for searching the vast chemical compound space and the stupendously many dynamical configurations that a molecule can assume. To overcome this challenge, recently there have been increased efforts to accelerate quantum simulations with machine learning (ML). This emerging interdisciplinary community encompasses chemists, material scientists, physicists, mathematicians and computer scientists, joining forces to contribute to the exciting hot topic of progressing machine learning and AI for molecules and materials. The book that has emerged from a series of workshops provides a snapshot of this rapidly developing field. It contains tutorial material explaining the relevant foundations needed in chemistry, physics as well as machine learning to give an easy starting point for interested readers. In addition, a number of research papers defining the current state-of-the-art are included. The book has five parts (Fundamentals, Incorporating Prior Knowledge, Deep Learning of Atomistic Representations, Atomistic Simulations and Discovery and Design), each prefaced by editorial commentary that puts the respective parts into a broader scientific context.

Machine Learning Meets Quantum Physics

Genevieve B. Orr

It is our belief that researchers and practitioners acquire, through experience and word-of-mouth, techniques and heuristics that help them successfully apply neural networks to di cult real world problems. Often these \tricks" are theo- tically well motivated. Sometimes they are the result of trial and error. However, their most common link is that they are usually hidden in people’s heads or in the back pages of space-constrained conference papers. As a result newcomers to the eld waste much time wondering why their networks train so slowly and perform so poorly. This book is an outgrowth of a 1996 NIPS workshop called Tricks of the Trade whose goal was to begin the process of gathering and documenting these tricks. The interest that the workshop generated motivated us to expand our collection and compile it into this book. Although we have no doubt that there are many tricks we have missed, we hope that what we have included will prove to be useful, particularly to those who are relatively new to the eld. Each chapter contains one or more tricks presented by a given author (or authors). We have attempted to group related chapters into sections, though we recognize that the di erent sections are far from disjoint. Some of the chapters (e.g., 1, 13, 17) contain entire systems of tricks that are far more general than the category they have been placed in.

Neural Networks: Tricks of the Trade

Grégoire Montavon

Geneviève Orr

The twenty last years have been marked by an increase in available data and computing power. In parallel to this trend, the focus of neural network research and the practice of training neural networks has undergone a number of important changes, for example, use of deep learning machines. The second edition of the book augments the first edition with more tricks, which have resulted from 14 years of theory and experimentation by some of the world's most prominent neural network researchers. These tricks can make a substantial difference (in terms of speed, ease of implementation, and accuracy) when it comes to putting algorithms to work on real problems.

Bertram Nickolay

Katrin Franke

Ralf Schäfer

This book constitutes the refereed proceedings of the 28th Symposium of the German Association for Pattern Recognition, DAGM 2006. The book presents 32 revised full papers and 44 revised poster papers together with 5 invited papers. Topical sections include image filtering, restoration and segmentation, shape analysis and representation, recognition, categorization and detection, computer vision and image retrieval, machine learning and statistical data analysis, biomedical data analysis, and more.

28th DAGM Symposium, Berlin, Germany, September 12-14, 2006, Proceedings

Pattern Recognition

Andrea Vedaldi

Wojciech Samek

Lars Kai Hansen

The development of “intelligent” systems that can take decisions and perform autonomously might lead to faster and more consistent decisions. A limiting factor for a broader adoption of AI technology is the inherent risks that come with giving up human control and oversight to “intelligent” machines. For sensitive tasks involving critical infrastructures and affecting human well-being or health, it is crucial to limit the possibility of improper, non-robust and unsafe decisions and actions. Before deploying an AI system, we see a strong need to validate its behavior, and thus establish guarantees that it will continue to perform as expected when deployed in a real-world environment. In pursuit of that objective, ways for humans to verify the agreement between the AI decision structure and their own ground-truth knowledge have been explored. Explainable AI (XAI) has developed as a subfield of AI, focused on exposing complex AI models to humans in a systematic and interpretable manner. The 22 chapters included in this book provide a timely snapshot of algorithms, theory, and applications of interpretable and explainable AI and AI techniques that have been proposed recently reflecting the current discourse in this field and providing directions of future development. The book is organized in six parts: towards AI transparency; methods for interpreting AI systems; explaining the decisions of AI systems; evaluating interpretability and explanations; applications of explainable AI; and software for explainable AI.

Explainable AI: Interpreting, Explaining and Visualizing Deep Learning

Klaus-Robert Müller

Books

Your next favorite book is out there