Thomas G. Dietterich

Bio: Thomas G. Dietterich is an academic researcher from Oregon State University. The author has contributed to research in topics: Reinforcement learning & Markov decision process. The author has an hindex of 74, co-authored 279 publications receiving 51935 citations. Previous affiliations of Thomas G. Dietterich include University of Wyoming & Stanford University.

Steps Toward Robust Artificial Intelligence

Abstract: Recent advances in artificial intelligence are encouraging governments and corporations to deploy AI in high-stakes settings including driving cars autonomously, managing the power grid, trading on stock exchanges, and controlling autonomous weapons systems. Such applications require AI methods to be robust to both the known unknowns (those uncertain aspects of the world about which the computer can reason explicitly) and the unknown unknowns (those aspects of the world that are not captured by the system’s models). This article discusses recent progress in AI and then describes eight ideas related to robustness that are being pursued within the AI research community. While these ideas are a start, we need to devote more attention to the challenges of dealing with the known and unknown unknowns. These issues are fascinating, because they touch on the fundamental question of how finite systems can survive and thrive in a complex and dangerous world

Structured machine learning: the next ten years

Abstract: The field of inductive logic programming (ILP) has made steady progress, since the first ILP workshop in 1991, based on a balance of developments in theory, implementations and applications. More recently there has been an increased emphasis on Probabilistic ILP and the related fields of Statistical Relational Learning (SRL) and Structured Prediction. The goal of the current paper is to consider these emerging trends and chart out the strategic directions and open problems for the broader area of structured machine learning for the next 10 years.

Learning and Inductive Inference

Abstract: : The main results of the report are: (a) a simple model that serves to generate a taxonomy of learning systems, (b) the explication and clarification of four methods of learning single concepts, (c) some understanding of the underlying causes of the credit-assignment problem (and possible solutions), and (d) some identification of open research problems and areas that have received little attention. The report is structured as a set of articles. Seven of the articles present the main problems and issues in learning research, while the remaining fifteen articles describe particular learning systems that have been developed.

Map Misclassification Can Cause Large Errors in Landscape Pattern Indices: Examples from Habitat Fragmentation

Abstract: Although habitat fragmentation is one of the greatest threats to biodiversity worldwide, virtually no attention has been paid to the quantification of error in fragmentation statistics. Landscape pattern indices (LPIs), such as mean patch size and number of patches, are routinely used to quantify fragmentation and are often calculated using remote-sensing imagery that has been classified into different land-cover classes. No classified map is ever completely correct, so we asked if different maps with similar misclassification rates could result in widely different errors in pattern indices. We simulated landscapes with varying proportions of habitat and clumpiness (autocorrelation) and then simulated classification errors on the same maps. We simulated higher misclassification at patch edges (as is often observed), and then used a smoothing algorithm routinely used on images to correct salt-and-pepper classification error. We determined how well classification errors (and smoothing) corresponded to errors seen in four pattern indices. Maps with low misclassification rates often yielded errors in LPIs of much larger magnitude and substantial variability. Although smoothing usually improved classification error, it sometimes increased LPI error and reversed the direction of error in LPIs introduced by misclassification. Our results show that classification error is not always a good predictor of errors in LPIs, and some types of image postprocessing (for example, smoothing) might result in the underestimation of habitat fragmentation. Furthermore, our results suggest that there is potential for large errors in nearly every landscape pattern analysis ever published, because virtually none quantify the errors in LPIs themselves.

High-Performance Job-Shop Scheduling With A Time-Delay TD(λ) Network

Abstract: Job-shop scheduling is an important task for manufacturing industries. We are interested in the particular task of scheduling payload processing for NASA's space shuttle program. This paper summarizes our previous work on formulating this task for solution by the reinforcement learning algorithm TD(λ). A shortcoming of this previous work was its reliance on hand-engineered input features. This paper shows how to extend the time-delay neural network (TDNN) architecture to apply it to irregular-length schedules. Experimental tests show that this TDNN-TD(λ) network can match the performance of our previous hand-engineered system. The tests also show that both neural network approaches significantly outperform the best previous (non-learning) solution to this problem in terms of the quality of the resulting schedules and the number of search steps required to construct them.

Random Forests

Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.

Gradient-based learning applied to document recognition

Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Going deeper with convolutions

Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

Deep Learning

Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Reinforcement Learning: An Introduction

Abstract: Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.