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

Autonomous navigation in unknown but wellstructured environments (e.g., parking lots) is a common task for human drivers and an important goal for autonomous vehicles. In such environments, the vehicles must obey the standard conventions of driving (e.g., passing oncoming vehicles on the correct side), but often lack a map that can be used to guide path planning in an appropriate way. The robots must therefore rely on features of the environment to drive in a safe and predictable way. In this work, we focus on detecting one of such features, the principal directions of the environment. We propose a Markov-random-field (MRF) model for estimating the maximum-likelihood field of principal directions, given the local linear features extracted from the vehicle’s sensor data, and show that the method leads to robust estimates of principal directions in complex real-life driving environments. We also demonstrate how the computed principal directions can be used to guide a path-planning algorithm, leading to the generation of significantly improved trajectories.

http://www.roboticsproceedings.org/rss04/p10.pdf

Detection of Principle Directions in Unknown Environments for Autonomous Navigation.

Summary form only given. The DARPA Grand Challenge was the most significant event in the field of robotics in more than a decade. A mobile ground robot had to traverse 132 miles of punishing desert terrain in less than ten hours. In 2004, the best robot only made 7.3 miles. A year later, Stanford won this historical challenge and cashed the } prize. This talk, delivered by the leader of the Stanford Racing Team, will provide insights into the software architecture of Stanford's winning robot "Stanley." The robot heavily relied on advanced artificial intelligence, and it used a pipelining architecture to turn sensor data into vehicle controls. The talk will introduce the audience into the fascinating world of autonomous robotics, share many of the race insights, and discuss some of the implications for the future of our society

Winning the DARPA Grand Challenge: A Robot Race through the Mojave Desert

Methods and devices for providing a user-interface are disclosed. In one embodiment, the method comprises receiving data corresponding to a first position of a wearable computing device and responsively causing the wearable computing device to provide a user-interface. The user-interfaces comprises a view region and a menu, where the view region substantially fills a field of view of the wearable computing device and the menu is not fully visible in the view region. The method further comprises receiving data indicating a selection of an item present in the view region and causing an indicator to be displayed in the view region, wherein the indicator changes incrementally over a length of time. When the length of time has passed, the method comprises responsively causing the wearable computing device to select the item.

Hands-Free Selection Using a Ring-Based User-Interface

: This paper describes CES, a prototype of a new programming language for robots and other embedded systems, equipped with sensors and actuators. CES contains two new ideas, currently not found in other programming languages: support of computing with uncertain information, and support of adaptation and teaching as a means of programming. These innovations facilitate the rapid development of software for embedded systems, as demonstrated by two mobile robot applications.

/pdf/a-framework-for-programming-embedded-systems-initial-design-54361pkubp.pdf

A Framework for Programming Embedded Systems: Initial Design and Results

We describe two robotic systems for acquiring high-resolution volumetric maps of underground mines. Our systems have been deployed in an operational coal mine in Bruceton, Pennsylvania, where they have been used to generate interactive 3-D maps. Our 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-D volumetric maps hundreds of meters in diameter, even when no odometry information is available.

Sebastian Thrun

Papers

Detection of Principle Directions in Unknown Environments for Autonomous Navigation.

Winning the DARPA Grand Challenge: A Robot Race through the Mojave Desert

Hands-Free Selection Using a Ring-Based User-Interface

A Framework for Programming Embedded Systems: Initial Design and Results

A System for Volumetric Robotic Mapping of Underground Mines