The dramatic success in machine learning has led to an explosion of artificial intelligence (AI) applications and increasing expectations for autonomous systems that exhibit human-level intelligence. These expectations have, however, met with fundamental obstacles that cut across many application areas. One such obstacle is adaptability, or robustness. Machine learning researchers have noted current systems lack the ability to recognize or react to new circumstances they have not been specifically programmed or trained for. Intensive theoretical and experimental efforts toward "transfer learning," "domain adaptation," and "lifelong learning"4 are reflective of this obstacle. Another obstacle is "explainability," or that "machine learning models remain mostly black boxes"26 unable to explain the reasons behind their predictions or recommendations, thus eroding users' trust and impeding diagnosis and repair; see Hutson8 and Marcus.11 A third obstacle concerns the lack of understanding of cause-effect connections.

Most work on interpretability in machine learning has focused on designing either inherently interpretable models, that typically trade-off interpretability for accuracy, or post-hoc explanation systems, that lack guarantees about their explanation quality. We propose an alternative to these approaches by directly regularizing a black-box model for interpretability at training time. Our approach explicitly connects three key aspects of interpretable machine learning: the model's innate explainability, the explanation system used at test time, and the metrics that measure explanation quality. Our regularization results in substantial (up to orders of magnitude) improvement in terms of explanation fidelity and stability metrics across a range of datasets, models, and black-box explanation systems. Remarkably, our regularizers also slightly improve predictive accuracy on average across the nine datasets we consider. Further, we show that the benefits of our novel regularizers on explanation quality provably generalize to unseen test points.

Artificial Intelligence is way overhyped. I remember well how over-hyped AI was back in the early 1980s when I worked with Applied Expert Systems, a startup founded by some MIT professors that aspired to use expert systems to transform the world of personal financial planning. I helped bring the software to the company and participated in so-called knowledge engineering by interviewing a personal financial planning expert. The idea was to convert the expert's decision making rules into software and build a system that would replace personal financial planners. Sadly for those who invested time and money in this company, its product never found much of a market and it folded.

Data shows that, for global businesses, providing support in multiple languages is well worth the effort. Nearly three quarters of people search online in their native language, which means that if you're only communicating in English, for example, you're probably losing customers and adding layers of inefficiencies for your agents. Easier said than done, perhaps. On average, even in one language, 20% of agent time is spent looking for information to either share directly with customers or to find the right way to resolve a problem. Providing support in multiple languages across multiple channels adds another set of variables to the mix.

In this paper, we present a novel approach for the task of eXplainable Question Answering (XQA), i.e., generating natural language (NL) explanations for the Visual Question Answering (VQA) problem. We generate NL explanations comprising of the evidence to support the answer to a question asked to an image using two sources of information: (a) annotations of entities in an image (e.g., object labels, region descriptions, relation phrases) generated from the scene graph of the image, and (b) the attention map generated by a VQA model when answering the question. We show how combining the visual attention map with the NL representation of relevant scene graph entities, carefully selected using a language model, can give reasonable textual explanations without the need of any additional collected data (explanation captions, etc). We run our algorithms on the Visual Genome (VG) dataset and conduct internal user-studies to demonstrate the efficacy of our approach over a strong baseline. We have also released a live web demo showcasing our VQA and textual explanation generation using scene graphs and visual attention.

A survey of early work exploring how AI can be used in medicine, with somewhat more technical expositions than in the complementary volume Artificial Intelligence in Medicine."Each chapter is preceded by a brief introduction that outlines our view of its contribution to the field, the reason it was selected for inclusion in this volume, an overview of its content, and a discussion of how the work evolved after the article appeared and how it relates to other chapters in the book.

The promise of ANNs to automatically discover and extract useful features/patterns from data without dwelling on domain expertise although seems highly promising but comes at the cost of high reliance on large amount of accurately labeled data, which is often hard to acquire and formulate especially in time-series domains like anomaly detection, natural disaster management, predictive maintenance and healthcare. As these networks completely rely on data and ignore a very important modality i.e. expert, they are unable to harvest any benefit from the expert knowledge, which in many cases is very useful. In this paper, we try to bridge the gap between these data driven and expert knowledge based systems by introducing a novel framework for incorporating expert knowledge into the network (KINN). Integrating expert knowledge into the network has three key advantages: (a) Reduction in the amount of data needed to train the model, (b) provision of a lower bound on the performance of the resulting classifier by obtaining the best of both worlds, and (c) improved convergence of model parameters (model converges in smaller number of epochs). Although experts are extremely good in solving different tasks, there are some trends and patterns, which are usually hidden only in the data. Therefore, KINN employs a novel residual knowledge incorporation scheme, which can automatically determine the quality of the predictions made by the expert and rectify it accordingly by learning the trends/patterns from data. Specifically, the method tries to use information contained in one modality to complement information missed by the other. We evaluated KINN on a real world traffic flow prediction problem. KINN significantly superseded performance of both the expert and as well as the base network (LSTM in this case) when evaluated in isolation, highlighting its superiority for the task.

Artificial intelligence, or AI, is largely an experimental science—at least as much progress has been made by building and analyzing programs as by examining theoretical questions. MYCIN is one of several well-known programs that embody some intelligence and provide data on the extent to which intelligent behavior can be programmed. As with other AI programs, its development was slow and not always in a forward direction. But we feel we learned some useful lessons in the course of nearly a decade of work on MYCIN and related programs. In this book we share the results of many experiments performed in that time, and we try to paint a coherent picture of the work. The book is intended to be a critical analysis of several pieces of related research, performed by a large number of scientists. We believe that the whole field of AI will benefit from such attempts to take a detailed retrospective look at experiments, for in this way the scientific foundations of the field will gradually be defined. It is for all these reasons that we have prepared this analysis of the MYCIN experiments.

This book has been adapted in large part from the author's doctoral thesis [Shortliffe, l 974b]. Portions of the work appeared previously in Computers And Biomedical Research [Shortliffe, 1973, l 975b], Mathematical Biosciences [Shortliffe, 1975a], and the Proceedings Of The Thirteenth San Diego Biomedical Symposium [Shortliffe, l 974a]. To Stanford's Medical Scientist Training Program, which is supported by the National Institutes of Health Contents

JANICE S. AIKINS Dr. Aikins received her Ph.D. in computer science from Stanford University in 1980. She is currently a research computer scientist at IBM's Palo Alto Scientific Center. She specializes in designing systems with an emphasis on the explicit representation of control knowledge in expert systems. ROBERT L. BLUM Dr. Blum received his M.D. from the University of California Medical School at San Francisco in 1973. From 1973 to 1976 he did an internship and residency in the Department of Internal Medicine at the Kaiser Foundation Hospital in Oakland, California, where he was chief resident in 1976.