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

We describe latent Dirichlet allocation (LDA), a generative probabilistic model for collections of discrete data such as text corpora. LDA is a three-level hierarchical Bayesian model, in which each item of a collection is modeled as a finite mixture over an underlying set of topics. Each topic is, in turn, modeled as an infinite mixture over an underlying set of topic probabilities. In the context of text modeling, the topic probabilities provide an explicit representation of a document. We present efficient approximate inference techniques based on variational methods and an EM algorithm for empirical Bayes parameter estimation. We report results in document modeling, text classification, and collaborative filtering, comparing to a mixture of unigrams model and the probabilistic LSI model.

/pdf/latent-dirichlet-allocation-4gmscb06en.pdf

Latent dirichlet allocation

We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI) [3]. In the context of text modeling, our model posits that each document is generated as a mixture of topics, where the continuous-valued mixture proportions are distributed as a latent Dirichlet random variable. Inference and learning are carried out efficiently via variational algorithms. We present empirical results on applications of this model to problems in text modeling, collaborative filtering, and text classification.

/pdf/latent-dirichlet-allocation-rkwbqihm3p.pdf

Latent Dirichlet Allocation

Data Mining: Practical Machine Learning Tools and Techniques offers a thorough grounding in machine learning concepts as well as practical advice on applying machine learning tools and techniques in real-world data mining situations. This highly anticipated third edition of the most acclaimed work on data mining and machine learning will teach you everything you need to know about preparing inputs, interpreting outputs, evaluating results, and the algorithmic methods at the heart of successful data mining. Thorough updates reflect the technical changes and modernizations that have taken place in the field since the last edition, including new material on Data Transformations, Ensemble Learning, Massive Data Sets, Multi-instance Learning, plus a new version of the popular Weka machine learning software developed by the authors. Witten, Frank, and Hall include both tried-and-true techniques of today as well as methods at the leading edge of contemporary research. *Provides a thorough grounding in machine learning concepts as well as practical advice on applying the tools and techniques to your data mining projects *Offers concrete tips and techniques for performance improvement that work by transforming the input or output in machine learning methods *Includes downloadable Weka software toolkit, a collection of machine learning algorithms for data mining tasks-in an updated, interactive interface. Algorithms in toolkit cover: data pre-processing, classification, regression, clustering, association rules, visualization

Data Mining: Practical Machine Learning Tools and Techniques

抗原变异可使得多种致病微生物易于逃避宿主免疫应答。表达在感染红细胞表面的恶性疟原虫红细胞表面蛋白1（PfPMP1）与感染红细胞、内皮细胞、树突状细胞以及胎盘的单个或多个受体作用，在黏附及免疫逃避中起关键的作用。每个单倍体基因组var基因家族编码约60种成员，通过启动转录不同的var基因变异体为抗原变异提供了分子基础。

疟原虫var基因转换速率变化导致抗原变异[英]／Paul H, Robert P, Christodoulou Z, et al//Proc Natl Acad Sci U S A

In this paper we propose an active control strategy for scanning laser sensors on autonomous vehicles traveling offroad at high speeds. As speed increases the amount of sensor information about the terrain decreases. We address the problem of sensor control in the context of this speed-coverage trade off. The algorithm and testing methodologies are described with results comparing our active sensing method to a passive sensing method.

/pdf/active-sensing-for-high-speed-offroad-driving-35wj2fw9aw.pdf

Active Sensing for High-Speed Offroad Driving

Traditional image mosaicing usually relies on rigid image transformations. In many medical applications, however, tissue deformation during image acquisition or 3D parallax effects may require nonrigid transformations in the mosaicing process. This paper presents a new method that integrates deformable surface models into the image mosaicing algorithms. Our approach has two main contributions. First, we present a global alignment algorithm to efficiently deal with accumulated image registration errors. Second, we introduce a local alignment algorithm to accommodate local scene deformations. These two problems are integrated into a single optimization problem that simultaneously recovers the motion of the camera as well as the structure of the scene. Our approach is demonstrated on simulations, images from a hand-held digital camera, and microscopic images acquired with a micro-endoscope.

Deformable Image Mosaicing for Optical Biopsy

: The authors describe two robotic systems for acquiring high-resolution volumetric maps of underground mines. Their systems have been deployed in an operational coal mine in Bruceton, Pennsylvania, where they have been used to generate interactive 3-dimensional maps. Their approach includes a novel sensor head assembled from multiple SICK laser range finders, and a real-time algorithm for scan matching that generates accurate volumetric maps. The scan matching algorithm performs horizontal and vertical simultaneous localization and mapping (SLAM). Data from the horizontal scans is used to remove artifacts in the vertical scans, and vice versa. The system can construct full 3-dimensional volumetric maps hundreds of meters in diameter, even when no odometry information is available.

A System for Three-Dimensional Robotic Mapping of Underground Mines

Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we present an algorithm for learning object models of non-stationary objects found in office-type environments. Our algorithm exploits the fact that many objects found in office environments look alike (e.g., chairs, recycling bins). It does so through a two-level hierarchical representation, which links individual objects with generic shape templates of object classes. We derive an approximate EM algorithm for learning shape parameters at both levels of the hierarchy, using local occupancy grid maps for representing shape. Additionally, we develop a Bayesian model selection algorithm that enables the robot to estimate the total number of objects and object templates in the environment. Experimental results using a real robot equipped with a laser range finder indicate that our approach performs well at learning object-based maps of simple office environments. The approach outperforms a previously developed non-hierarchical algorithm that models objects but lacks class templates.

Learning Hierarchical Object Maps Of Non-Stationary Environments with mobile robots

Explanation-based neural network learning (EBNN) has recently been proposed as a method for reducing the amount of training data required for reliable generalization, by relying instead on approximate, previously learned knowledge. We present first experiments applying EBNN to the problem of learning object recognition for a mobile robot. In these experiments, a mobile robot traveling down a hallway corridor learns to recognize distant doors based on color camera images and sonar sensations. The previously learned knowledge corresponds to a neural network that recognizes nearby doors, and a second network that predicts the state of the world after travelling forward in the corridor. Experimental results show that EBNN is able to use this approximate prior knowledge to significantly reduce the number of training examples required to learn to recognize distant doors. We also present results of experiments in which networks learned by EBNN (e.g., "there is a door 2 meters ahead") are then used as background knowledge for learning subsequent functions (e.g., "there is a door 3 meters ahead").

/pdf/explanation-based-learning-for-mobile-robot-perception-3w0q0vi94y.pdf

Sebastian Thrun

Papers

Active Sensing for High-Speed Offroad Driving

Deformable Image Mosaicing for Optical Biopsy

A System for Three-Dimensional Robotic Mapping of Underground Mines

Learning Hierarchical Object Maps Of Non-Stationary Environments with mobile robots

Explanation-based learning for mobile-robot perception