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

This paper presents a nonlinear control law for an automobile to autonomously track a trajectory, provided in real-time, on rapidly varying, off-road terrain. Existing methods can suffer from a lack of global stability, a lack of tracking accuracy, or a dependence on smooth road surfaces, any one of which could lead to the loss of the vehicle in autonomous off-road driving. This work treats automobile trajectory tracking in a new manner, by considering the orientation of the front wheels - not the vehicle's body - with respect to the desired trajectory, enabling collocated control of the system. A steering control law is designed using the kinematic equations of motion, for which global asymptotic stability is proven. This control law is then augmented to handle the dynamics of pneumatic tires and of the servo-actuated steering wheel. To control vehicle speed, the brake and throttle are actuated by a switching proportional integral (PI) controller. The complete control system consumes a negligible fraction of a computer's resources. It was implemented on a Volkswagen Touareg, "Stanley", the Stanford Racing Team's entry in the DARPA Grand Challenge 2005, a 132 mi autonomous off-road race. Experimental results from Stanley demonstrate the ability of the controller to track trajectories between obstacles, over steep and wavy terrain, through deep mud puddles, and along cliff edges, with a typical root mean square (RMS) crosstrack error of under 0.1 m. In the DARPA National Qualification Event 2005, Stanley was the only vehicle out of 40 competitors to not hit an obstacle or miss a gate, and in the DARPA Grand Challenge 2005 Stanley had the fastest course completion time.

/pdf/autonomous-automobile-trajectory-tracking-for-off-road-4kdtc5m23a.pdf

Autonomous Automobile Trajectory Tracking for Off-Road Driving: Controller Design, Experimental Validation and Racing

This paper describes the state-of-the art of a large-scale project, aimed towards the development of personal service robots for the elderly population. Taking care of elderly and chronically ill people is one of the major challenges currently faced by society. Needs range from increasing articulation to assisting those with dementia and cognitive impairment. To respond to this challenge, we have developed a first prototype robot. Using natural language, the robot can provide information related to activities of daily living obtained from the Web. It also enables remote care-givers to establish a “tele-presence” in people’s home, by relaying back video and audio stream through the Next Generation Internet. The paper describes this early prototype, and it lays out our research agenda towards building service robots for the elderly.

/pdf/towards-personal-service-robots-for-the-elderly-284hnbgpey.pdf

Towards Personal Service Robots for the Elderly

This paper describes an implemented robot system, which relies heavily on probabilistic AI techniques for acting under uncertainty. The robot Pearl and its predecessor Flo have been developed by a multi-disciplinary team of researchers over the past three years. The goal of this research is to investigate the feasibility of assisting elderly people with cognitive and physical activity limitations through interactive robotic devices, thereby improving their quality of life. The robot's task involves escorting people in an assisted living facility-a time-consuming task currently carried out by nurses. Its software architecture employs probabilistic techniques at virtually all levels of perception and decision making. During the course of experiments conducted in an assisted living facility, the robot successfully demonstrated that it could autonomously provide guidance for elderly residents. While previous experiments with fielded robot systems have provided evidence that probabilistic techniques work well in the context of navigation, we found the same to be true of human robot interaction with elderly people.

/pdf/experiences-with-a-mobile-robotic-guide-for-the-elderly-4bdhdz36kk.pdf

Experiences with a mobile robotic guide for the elderly

Exploration plays a fundamental role in any active learning system. This study evaluates the role of exploration in active learning and describes several local techniques for exploration in finite, discrete domains, embedded in a reinforcement learning framework (delayed reinforcement). This paper distinguishes between two families of exploration schemes: undirected and directed exploration. While the former family is closely related to random walk exploration, directed exploration techniques memorize exploration-specific knowledge which is used for guiding the exploration search. In many finite deterministic domains, any learning technique based on undirected exploration is inefficient in terms of learning time, i.e., learning time is expected to scale exponentially with the size of the state space. We prove that for all these domains, reinforcement learning using a directed technique can always be performed in polynomial time, demonstrating the important role of exploration in reinforcement learning. (The proof is given for one specific directed exploration technique named counter-based exploration.) Subsequently, several exploration techniques found in recent reinforcement learning and connectionist adaptive control literature are described. In order to trade off efficiently between exploration and exploitation --- a trade-off which characterizes many real-world active learning tasks --- combination methods are described which explore and avoid costs simultaneously. This includes a selective attention mechanism, which allows smooth switching between exploration and exploitation. All techniques are evaluated and compared on a discrete reinforcement learning task (robot navigation). The empirical evaluation is followed by an extensive discussion of benefits and limitations of this work.

Efficient Exploration In Reinforcement Learning

We present a Monte Carlo algorithm for learning to act in partially observable Markov decision processes (POMDPs) with real-valued state and action spaces. Our approach uses importance sampling for representing beliefs, and Monte Carlo approximation for belief propagation. A reinforcement learning algorithm, value iteration, is employed to learn value functions over belief states. Finally, a sample-based version of nearest neighbor is used to generalize across states. Initial empirical results suggest that our approach works well in practical applications.

Sebastian Thrun

Papers

Autonomous Automobile Trajectory Tracking for Off-Road Driving: Controller Design, Experimental Validation and Racing

Towards Personal Service Robots for the Elderly

Experiences with a mobile robotic guide for the elderly

Efficient Exploration In Reinforcement Learning

Monte Carlo POMDPs