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

We demonstrate the transfer of learning from an ensemble of background tasks, which becomes helpful in cases where a single background task does not transfer well. This approach is accomplished through a simple maximum a posteriori elaboration on the logistic regression approach and tested on real world data. 1 Transfer Learning Via Learned Prior Distributions Transferring knowledge from a famil iar domain or task (call it task A) to an unfamiliar or newly-encountered one (task B) is a fundamental and fascinating aspect of human learning. Although the motivating notion is intuitive, the simple approach of treating the two tasks as identical and pooling their training data does not usually work well. This is presumably because the decision boundaries for A and B are not in exactly the same places in the feature space, even when the feature spaces and input distributions are themselves identical. Hence, more sophisticated methods are required. One interesting approach is to treat task A as defining a form of Bayesian prior distribution for task B. In this paper, we study this approach in a setting where we have many task As and only one task B, and we study whether we can learn a useful prior from those multiple task As that gives effective guidance when learning task B. Consider the well-known logistic regression model,

/pdf/transfer-learning-with-an-ensemble-of-background-tasks-19nyl4urnk.pdf

Transfer Learning with an Ensemble of Background Tasks

Where a legacy of aggressive wildland fire suppression has left forests in need of fuel reduction, allowing wildland fire to burn may provide fuel treatment benefits, thereby reducing suppression costs from subsequent fires. The least-cost-plus-net-value-change model of wildland fire economics includes benefits of wildfire in a framework for evaluating suppression options. In this study, we estimated one component of that benefit - the expected present value of the reduction in suppression costs for subsequent fires arising from the fuel treatment effect of a current fire. To that end, weemployedMonteCarlomethodstogenerateasetofscenariosforsubsequentfireignitionandweatherevents,whichare referred to as sample paths, for a study area in central Oregon. We simulated fire on the landscape over a 100-year time horizon using existing models of fire behaviour, vegetation and fuels development, and suppression effectiveness, and we estimatedsuppressioncostsusinganexistingsuppressioncostmodel.Ourestimatessuggestthatthepotentialcostsavings may be substantial. Further research is needed to estimate the full least-cost-plus-net-value-change model. This line of research will extend the set of tools available for developing wildfire management plans for forested landscapes. Additional keywords: bio-economic modelling, forest economics, forest fire policy, wildland fire management.

/pdf/allowing-a-wildfire-to-burn-estimating-the-effect-on-future-27u406jkvq.pdf

Allowing a wildfire to burn: estimating the effect on future fire suppression costs

We consider the problem of incorporating end-user advice into reinforcement learning (RL). In our setting, the learner alternates between practicing, where learning is based on actual world experience, and end-user critique sessions where advice is gathered. During each critique session the end-user is allowed to analyze a trajectory of the current policy and then label an arbitrary subset of the available actions as good or bad. Our main contribution is an approach for integrating all of the information gathered during practice and critiques in order to effectively optimize a parametric policy. The approach optimizes a loss function that linearly combines losses measured against the world experience and the critique data. We evaluate our approach using a prototype system for teaching tactical battle behavior in a real-time strategy game engine. Results are given for a significant evaluation involving ten end-users showing the promise of this approach and also highlighting challenges involved in inserting end-users into the RL loop.

/pdf/reinforcement-learning-via-practice-and-critique-advice-1cwb2qutl7.pdf

Reinforcement learning via practice and critique advice

The ecological sciences have benefited greatly from recent advances in wireless sensor technologies. These technologies allow researchers to deploy networks of automated sensors, which can monitor a landscape at very fine temporal and spatial scales. However, these networks are subject to harsh conditions, which lead to malfunctions in individual sensors and failures in network communications. The resulting data streams often exhibit incorrect data measurements and missing values. Identifying and correcting these is time-consuming and error-prone. We present a method for real-time automated data quality control (QC) that exploits the spatial and temporal correlations in the data to distinguish sensor failures from valid observations. The model adapts to each deployment site by learning a Bayesian network structure that captures spatial relationships between sensors, and it extends the structure to a dynamic Bayesian network to incorporate temporal correlations. This model is able to flag faulty observations and predict the true values of the missing or corrupt readings. The performance of the model is evaluated on data collected by the SensorScope Project. The results show that the spatiotemporal model demonstrates clear advantages over models that include only temporal or only spatial correlations, and that the model is capable of accurately imputing corrupted values.

/pdf/spatiotemporal-models-for-data-anomaly-detection-in-dynamic-4smvi5wuat.pdf

Thomas G. Dietterich

Papers

Transfer Learning with an Ensemble of Background Tasks

Allowing a wildfire to burn: estimating the effect on future fire suppression costs

Reinforcement learning via practice and critique advice

Spatiotemporal Models for Data-Anomaly Detection in Dynamic Environmental Monitoring Campaigns

Learning to Predict Sequences