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.

Random Forests

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.

Gradient-based learning applied to document recognition

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.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

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.

Deep Learning

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.

/pdf/reinforcement-learning-an-introduction-rzxgej9p17.pdf

Reinforcement Learning: An Introduction

Open category detection is the problem of detecting "alien" test instances that belong to categories or classes that were not present in the training data. In many applications, reliably detecting such aliens is central to ensuring the safety and accuracy of test set predictions. Unfortunately, there are no algorithms that provide theoretical guarantees on their ability to detect aliens under general assumptions. Further, while there are algorithms for open category detection, there are few empirical results that directly report alien detection rates. Thus, there are significant theoretical and empirical gaps in our understanding of open category detection. In this paper, we take a step toward addressing this gap by studying a simple, but practically-relevant variant of open category detection. In our setting, we are provided with a "clean" training set that contains only the target categories of interest and an unlabeled "contaminated" training set that contains a fraction $\alpha$ of alien examples. Under the assumption that we know an upper bound on $\alpha$, we develop an algorithm with PAC-style guarantees on the alien detection rate, while aiming to minimize false alarms. Empirical results on synthetic and standard benchmark datasets demonstrate the regimes in which the algorithm can be effective and provide a baseline for further advancements.

/pdf/open-category-detection-with-pac-guarantees-4qdqk40ef4.pdf

Open Category Detection with PAC Guarantees

Many real-world domains exhibit rich relational structure and stochasticity and motivate the development of models that combine predicate logic with probabilities. These models describe probabilistic influences between attributes of objects that are related to each other through known domain relationships. To keep these models succinct, each such influence is considered independent of others, which is called the assumption of "independence of causal influences" (ICI). In this paper, we describe a language that consists of quantified conditional influence statements and captures most relational probabilistic models based on directed graphs. The influences due to different statements are combined using a set of combining rules such as Noisy-OR. We motivate and introduce multi-level combining rules, where the lower level rules combine the influences due to different ground instances of the same statement, and the upper level rules combine the influences due to different statements. We present algorithms and empirical results for parameter learning in the presence of such combining rules. Specifically, we derive and implement algorithms based on gradient descent and expectation maximization for different combining rules and evaluate them on synthetic data and on a real-world task. The results demonstrate that the algorithms are able to learn both the conditional probability distributions of the influence statements and the parameters of the combining rules.

Learning first-order probabilistic models with combining rules

In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in some cases. In this paper, we consider active imitation learning with the goal of reducing this effort by querying the expert about the desired action at individual states, which are selected based on answers to past queries and the learner's interactions with an environment simulator. We introduce a new approach based on reducing active imitation learning to i.i.d. active learning, which can leverage progress in the i.i.d. setting. Our first contribution, is to analyze reductions for both non-stationary and stationary policies, showing that the label complexity (number of queries) of active imitation learning can be substantially less than passive learning. Our second contribution, is to introduce a practical algorithm inspired by the reductions, which is shown to be highly effective in four test domains compared to a number of alternatives.

/pdf/active-imitation-learning-via-reduction-to-i-i-d-active-2ybn62cxx0.pdf

Active imitation learning via reduction to I.I.D. active learning

We study the problem of approximate inference in collective graphical models (CGMs), which were recently introduced to model the problem of learning and inference with noisy aggregate observations. We first analyze the complexity of inference in CGMs: unlike inference in conventional graphical models, exact inference in CGMs is NP-hard even for tree-structured models. We then develop a tractable convex approximation to the NP-hard MAP inference problem in CGMs, and show how to use MAP inference for approximate marginal inference within the EM framework. We demonstrate empirically that these approximation techniques can reduce the computational cost of inference by two orders of magnitude and the cost of learning by at least an order of magnitude while providing solutions of equal or better quality.

/pdf/approximate-inference-in-collective-graphical-models-5d0slvp2wg.pdf

Approximate Inference in Collective Graphical Models

The TaskTracer system allows knowledge workers to define a set of activities that characterize their desktop work. It then associates with each user-defined activity the set of resources that the user accesses when performing that activity. In order to correctly associate resources with activities and provide useful activity-related services to the user, the system needs to know the current activity of the user at all times. It is often convenient for the user to explicitly declare which activity he/she is working on. But frequently the user forgets to do this. TaskTracer applies machine learning methods to detect undeclared activity switches and predict the correct activity of the user. This paper presents TaskPredictor2, a complete redesign of the activity predictor in TaskTracer and its notification user interface. TaskPredictor2 applies a novel online learning algorithm that is able to incorporate a richer set of features than our previous predictors. We prove an error bound for the algorithm and present experimental results that show improved accuracy and a 180-fold speedup on real user data. The user interface supports negotiated interruption and makes it easy for the user to correct both the predicted time of the task switch and the predicted activity.

/pdf/detecting-and-correcting-user-activity-switches-algorithms-59yxrotpdo.pdf

Thomas G. Dietterich

Papers

Open Category Detection with PAC Guarantees

Learning first-order probabilistic models with combining rules

Active imitation learning via reduction to I.I.D. active learning

Approximate Inference in Collective Graphical Models

Detecting and correcting user activity switches: algorithms and interfaces