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

Methods, systems, devices and arrangements are implemented for motion tracking. One such system for tracking at least one object articulated in three-dimensional space is implemented using data obtained from a depth sensor. The system includes at least one processing circuit configured and arranged to determine location probabilities for a plurality of object parts by identifying, from image data obtained from the depth sensor, features of the object parts. The processing circuit selects a set of poses for the at least one object based upon the determined location probabilities and generates modeled depth sensor data by applying the selected set of poses to a model of the at least one object. The processing circuit selects a pose for the at least one object model-based based upon a probabilistic comparison between the data obtained from the depth sensor and the modeled depth sensor data.

Motion Capture Using Intelligent Part Identification

This paper present a multi-agent architecture for coordinating large numbers of mobile agents (e.g. robots) cooperating in uncertain environments. In particular, the Canadian Traveler Problem (CTP) is the problem of nding a shortest path to a goal location in a graph, where individual edges of the graph might or might not be traversable[1]. The agent has an initial probabilistic knowledge about the states of the edges. Whether or not an edge is traversable can only be found out by moving there. Hence, an optimal solution to a CTP is a contingency plan, which o ers alternative routes if edges are not available. Finding an optimal contingency plan is known to be NP-hard. We focus on the multi-agent CTP, which involves multiple agents attempting to reach multiple target locations. Finding an optimal solution is even harder, since the space of actions at each point in time is exponential in the number of agents. Our multi-agent architecture approaches the above mentioned set of intractable problems in an eÆcient, real-time manner. The architecture supports a large number of mobile, goal-driven information agents that strive to maximize their reward for reaching goals. These agents are coordinated at a higher level by dispatcher agents whose purpose is to maximize the total reward accumulated over time. Extensive experimental results have been obtained in the context of natural disaster relief. Our experiments have been carried out in a realistic simulation of Honduras after Hurricane Mitch destroyed most of the country's infrastructure.

/pdf/a-system-for-multi-agent-coordination-in-uncertain-7m9l4raj18.pdf

A system for multi-agent coordination in uncertain environments

Clustering is a ubiquitous task in data science. Compared to the commonly used $k$-means clustering, $k$-medoids clustering requires the cluster centers to be actual data points and support arbitrary distance metrics, which permits greater interpretability and the clustering of structured objects. Current state-of-the-art $k$-medoids clustering algorithms, such as Partitioning Around Medoids (PAM), are iterative and are quadratic in the dataset size $n$ for each iteration, being prohibitively expensive for large datasets. We propose BanditPAM, a randomized algorithm inspired by techniques from multi-armed bandits, that reduces the complexity of each PAM iteration from $O(n^2)$ to $O(n \log n)$ and returns the same results with high probability, under assumptions on the data that often hold in practice. As such, BanditPAM matches state-of-the-art clustering loss while reaching solutions much faster. We empirically validate our results on several large real-world datasets, including a coding exercise submissions dataset, the 10x Genomics 68k PBMC single-cell RNA sequencing dataset, and the MNIST handwritten digits dataset. In these experiments, we observe that BanditPAM returns the same results as state-of-the-art PAM-like algorithms up to 4x faster while performing up to 200x fewer distance computations. The improvements demonstrated by BanditPAM enable $k$-medoids clustering on a wide range of applications, including identifying cell types in large-scale single-cell data and providing scalable feedback for students learning computer science online. We also release highly optimized Python and C++ implementations of our algorithm.

BanditPAM: Almost Linear Time $k$-Medoids Clustering via Multi-Armed Bandits

Integrating topological and metric maps for mobile robot navigation

Physical Human Robot Interaction and Haptics.- Session Overview Physical Human-Robot Integration and Haptics.- A Unified Passivity Based Control Framework for Position, Torque and Impedance Control of Flexible Joint Robots.- Wave Haptics: Encoderless Virtual Stiffnesses.- Reality-Based Estimation of Needle and Soft-Tissue Interaction for Accurate Haptic Feedback in Prostate Brachytherapy Simulation.- Haptic Virtual Fixtures for Robot-Assisted Manipulation.- Planning.- Session Overview Planning.- POMDP Planning for Robust Robot Control.- On the Probabilistic Foundations of Probabilistic Roadmap Planning.- Humanoids.- Session Overview Humanoids.- Humanoid HRP2-DHRC for Autonomous and Interactive Behavior.- Android Science.- Mimetic Communication Theory for Humanoid Robots Interacting with Humans.- Mechanism and Design.- Session Overview Mechanisms and Design.- Design of a Compact 6-DOF Haptic Device to Use Parallel Mechanisms.- Hybrid Nanorobotic Approaches to NEMS.- Jacobian, Manipulability, Condition Number and Accuracy of Parallel Robots.- SLAM.- Session Overview Simultaneous Localisation and Mapping.- Subjective Localization with Action Respecting Embedding.- D-SLAM: Decoupled Localization and Mapping for Autonomous Robots.- A Provably Consistent Method for Imposing Sparsity in Feature-Based SLAM Information Filters.- Field Robots.- Session Overview Field Robotics.- Field D*: An Interpolation-Based Path Planner and Replanner.- Tradeoffs Between Directed and Autonomous Driving on the Mars Exploration Rovers.- Surface Mining: Main Research Issues for Autonomous Operations.- Robotic Vision.- Session Overview Robotic Vision.- Bias Reduction and Filter Convergence for Long Range Stereo.- Fusion of Stereo, Colour and Contrast.- Automatic Single-Image 3d Reconstructions of Indoor Manhattan World Scenes.- Robot Design and Control.- Session Overview Robot Design and Control.- One Is Enough!.- A Steerable, Untethered, 250 x 60 m MEMS Mobile Micro-Robot.- Some Issues in Humanoid Robot Design.- That Which Does Not Stabilize, Will Only Make Us Stronger.- Underwater Robotics.- Session Overview Underwater Robotics.- Improved Estimation of Target Velocity Using Multiple Model Estimation and a Dynamic Bayesian Network for a Robotic Tracker of Ocean Animals.- Techniques for Deep Sea Near Bottom Survey Using an Autonomous Underwater Vehicle.- Advances in High Resolution Imaging from Underwater Vehicles.- Learning and Adaptive Behavior.- Session Overview Learning and Adaptive Behavior.- Using AdaBoost for Place Labeling and Topological Map Building.- Emergence, Exploration and Learning of Embodied Behavior.- Hierarchical Conditional Random Fields for GPS-Based Activity Recognition.- Networked Robotics.- Session Overview Networked Robotics.- Networked Robotic Cameras for Collaborative Observation of Natural Environments.- Interfaces and Interaction.- Session Overview Interfaces and Interaction.- Haptic Communication Between Humans and Robots.- A Vestibular Interface for Natural Control of Steering in the Locomotion of Robotic Artifacts: Preliminary Experiments.- How Social Robots Will Help Us to Diagnose, Treat, and Understand Autism.- Invited Overview Talk.- Expo 2005 Robotics Project.- Robotics Science (Panel Discussion).- Position Statement: Robotics Science.

Sebastian Thrun

Papers

Motion Capture Using Intelligent Part Identification

A system for multi-agent coordination in uncertain environments

BanditPAM: Almost Linear Time $k$-Medoids Clustering via Multi-Armed Bandits

Integrating topological and metric maps for mobile robot navigation

Robotics research : results of the 12th International Symposium ISRR