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 proposes the dynamic window approach to reactive collision avoidance for mobile robots equipped with synchro-drives. The approach is derived directly from the motion dynamics of the robot and is therefore particularly well-suited for robots operating at high speed. It differs from previous approaches in that the search for commands controlling the translational and rotational velocity of the robot is carried out directly in the space of velocities. The advantage of our approach is that it correctly and in a rigorous way incorporates the dynamics of the robot. This is done by reducing the search space to the dynamic window, which consists of the velocities reachable within a short time interval. Within the dynamic window the approach only considers admissible velocities yielding a trajectory on which the robot is able to stop safely. Among these velocities the combination of translational and rotational velocity is chosen by maximizing an objective function. The objective function includes a measure of progress towards a goal location, the forward velocity of the robot, and the distance to the next obstacle on the trajectory. In extensive experiments the approach presented here has been found to safely control our mobile robot RHINO with speeds of up to 95 cm/sec, in populated and dynamic environments.

Controlling synchro-drive robots with the dynamic window approach to collision avoidance

Describes an online algorithm for generating compact 3D maps of mobile robot environments. Maps generated by our approach consist of small numbers of planar surfaces, which are augmented by fine-grained polygons for non-flat environmental features. Our approach builds on the expectation maximization (EM) algorithm, but develops a new, incremental version that can be executed in real-time. Experimental results obtained in corridor-type environments illustrate that compact and accurate maps can be acquired in real-time, from range and camera data collected by a mobile robot.

Real-time acquisition of compact volumetric 3D maps with mobile robots

Accurate perception is a principal challenge of autonomous off-road driving. Perceptive technologies generally focus on obstacle avoidance. However, at high speed, terrain roughness is also important to control shock the vehicle experiences. The accuracy required to detect rough terrain is significantly greater than that necessary for obstacle avoidance.

We present a self-supervised machine learning approach for estimating terrain roughness from laser range data. Our approach compares sets of nearby surface points acquired with a laser. This comparison is challenging due to uncertainty. For example, at range, laser readings may be so sparse that significant information about the surface is missing. Also, a high degree of precision is required when projecting laser readings. This precision may be unavailable due to latency or error in pose estimation. We model these sources of error as a multivariate polynomial. The coefficients of this polynomial are obtained through a self-supervised learning process. The "labels" of terrain roughness are automatically generated from actual shock, measured when driving over the target terrain. In this way, the approach provides its own training labels. It "transfers" the ability to measure terrain roughness from the vehicle's inertial sensors to its range sensors. Thus, the vehicle can slow before hitting rough terrain.

Our experiments use data from the 2005 DARPA Grand Challenge. We find our approach is substantially more effective at identifying rough surfaces and assuring vehicle safety than previous methods - often by as much as 50%.

/pdf/a-self-supervised-terrain-roughness-estimator-for-off-road-4opruykxdf.pdf

A self-supervised terrain roughness estimator for off-road autonomous driving

Vehicles are evolving into autonomous mobile-connected platforms. The rationale resides on the political and economic will towards a sustainable environment as well as advances in information and communication technologies that are rapidly being introduced into modern passenger vehicles. From a user perspective, safety and convenience are always a major concern. Further, new vehicles should enable people to drive that presently can not as well as to facilitate the continued mobility of the aging population. Advances are led by endeavors from vehicle manufacturers, the military and academia and development of sensors applicable to ground vehicles. Initially, the motivators are detailed on the reasons that vehicles are being built with intelligent capabilities. An outline of the navigation problem is presented to provide an understanding of the functions needed for a vehicle to navigate autonomously. In order to provide an overall perspective on how technology is converging towards vehicles with autonomous capabilities, advances have been classified into driver centric, network centric and vehicle centric. Vehicle manufacturers are introducing at a rapid pace Advanced Driving Assistance Systems; these are considered as Driver Centric with all functions facilitating driver awareness. This has resulted on the introduction of perception sensors utilizable in traffic situations and technologies that are advancing from simple (targeted to inform drivers) towards the control of the vehicle. The introduction of wireless links onboard vehicles should enable the sharing of information and thus enlarge the situational awareness of drivers as the perceived area is enlarged. Network Centric vehicles provide the means to perceive areas that vehicle onboard sensors alone can not observe and thus grant functions that allow for the deployment of vehicles with autonomous capabilities. Finally, vehicle centric functions are examined; these apply directly to the deployment of autonomous vehicles. Efforts in this realm are not new and thus fundamental work in this area is included. Sensors capable to detect objects in the road network are identified as dictating the pace of developments. The availability of intelligent sensors, advanced digital maps, and wireless communications technologies together with the availability of electric vehicles should allow for deployment on public streets without any environment modification. Likely, there will first be self-driving cars followed by environment modifications to facilitate their deployment.

Autonomous Driving: Context and State-of-the-Art

A system and process of morphing location-referenced panoramic images into views at nearby locations. When using panoramic images in an interactive tour, a user might desire to see the environment from viewpoints for which no panoramic images are available. This invention makes this possible. It enables a user to experience views from arbitrary locations in the environment, so as long as one or more panoramic images are available at nearby locations. In particular, this invention makes it possible to combine two non-overlapping geo-referenced panoramic video streams into a new video stream which seamlessly transitions between these streams. When used in a client-server architecture, this invention also makes it possible for the server to transmit a sparse sequence of panoramic images, and provide the user with a dense panoramic video stream, by synthesizing the missing panoramic images. Said system and process is also applicable to incomplete panoramic images, photographs, and video.

Sebastian Thrun

Papers

Controlling synchro-drive robots with the dynamic window approach to collision avoidance

Real-time acquisition of compact volumetric 3D maps with mobile robots

A self-supervised terrain roughness estimator for off-road autonomous driving

Autonomous Driving: Context and State-of-the-Art

System and process for synthesizing location-referenced panoramic images and video