MOOC Platforms
Total Page:16
File Type:pdf, Size:1020Kb
Load more
Recommended publications
-
Artificial Intelligence? 1 V2.0 © J
TU Darmstadt, WS 2012/13 Einführung in die Künstliche Intelligenz Einführung in die Künstliche Intelligenz Dozenten Prof. Johannes Fürnkranz (Knowledge Engineering) Prof. Ulf Brefeld (Knowledge Mining and Assessment) Homepage http://www.ke.informatik.tu-darmstadt.de/lehre/ki/ Termine: Dienstag 11:40-13:20 S202/C205 Donnerstag 11:40-13:20 S202/C205 3 VO + 1 UE Vorlesungen und Übungen werden in Doppelstunden abgehalten Übungen Terminplan wird auf der Web-Seite aktualisiert Ü voraussichtlich: 30.10., 13.11., 27.11., 11.12., 15.1., 29.1. Tafelübungen What is Artificial Intelligence? 1 V2.0 © J. Fürnkranz TU Darmstadt, WS 2012/13 Einführung in die Künstliche Intelligenz Text Book The course will mostly follow Stuart Russell und Peter Norvig: Artificial Intelligence: A Modern Approach. Prentice Hall, 2nd edition, 2003. Deutsche Ausgabe: Stuart Russell und Peter Norvig: Künstliche Intelligenz: Ein Moderner Ansatz. Pearson- Studium, 2004. ISBN: 978-3-8273-7089-1. 3. Auflage 2012 Home-page for the book: http://aima.cs.berkeley.edu/ Course slides in English (lecture is in German) will be availabe from Home-page What is Artificial Intelligence? 2 V2.0 © J. Fürnkranz TU Darmstadt, WS 2012/13 Einführung in die Künstliche Intelligenz What is Artificial Intelligence Different definitions due to different criteria Two dimensions: Thought processes/reasoning vs. behavior/action Success according to human standards vs. success according to an ideal concept of intelligence: rationality. Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally What is Artificial Intelligence? 3 V2.0 © J. Fürnkranz TU Darmstadt, WS 2012/13 Einführung in die Künstliche Intelligenz Definitions of Artificial Intelligence What is Artificial Intelligence? 4 V2.0 © J. -
The Machine That Builds Itself: How the Strengths of Lisp Family
Khomtchouk et al. OPINION NOTE The Machine that Builds Itself: How the Strengths of Lisp Family Languages Facilitate Building Complex and Flexible Bioinformatic Models Bohdan B. Khomtchouk1*, Edmund Weitz2 and Claes Wahlestedt1 *Correspondence: [email protected] Abstract 1Center for Therapeutic Innovation and Department of We address the need for expanding the presence of the Lisp family of Psychiatry and Behavioral programming languages in bioinformatics and computational biology research. Sciences, University of Miami Languages of this family, like Common Lisp, Scheme, or Clojure, facilitate the Miller School of Medicine, 1120 NW 14th ST, Miami, FL, USA creation of powerful and flexible software models that are required for complex 33136 and rapidly evolving domains like biology. We will point out several important key Full list of author information is features that distinguish languages of the Lisp family from other programming available at the end of the article languages and we will explain how these features can aid researchers in becoming more productive and creating better code. We will also show how these features make these languages ideal tools for artificial intelligence and machine learning applications. We will specifically stress the advantages of domain-specific languages (DSL): languages which are specialized to a particular area and thus not only facilitate easier research problem formulation, but also aid in the establishment of standards and best programming practices as applied to the specific research field at hand. DSLs are particularly easy to build in Common Lisp, the most comprehensive Lisp dialect, which is commonly referred to as the “programmable programming language.” We are convinced that Lisp grants programmers unprecedented power to build increasingly sophisticated artificial intelligence systems that may ultimately transform machine learning and AI research in bioinformatics and computational biology. -
Backpropagation with Callbacks
Backpropagation with Continuation Callbacks: Foundations for Efficient and Expressive Differentiable Programming Fei Wang James Decker Purdue University Purdue University West Lafayette, IN 47906 West Lafayette, IN 47906 [email protected] [email protected] Xilun Wu Grégory Essertel Tiark Rompf Purdue University Purdue University Purdue University West Lafayette, IN 47906 West Lafayette, IN, 47906 West Lafayette, IN, 47906 [email protected] [email protected] [email protected] Abstract Training of deep learning models depends on gradient descent and end-to-end differentiation. Under the slogan of differentiable programming, there is an increas- ing demand for efficient automatic gradient computation for emerging network architectures that incorporate dynamic control flow, especially in NLP. In this paper we propose an implementation of backpropagation using functions with callbacks, where the forward pass is executed as a sequence of function calls, and the backward pass as a corresponding sequence of function returns. A key realization is that this technique of chaining callbacks is well known in the programming languages community as continuation-passing style (CPS). Any program can be converted to this form using standard techniques, and hence, any program can be mechanically converted to compute gradients. Our approach achieves the same flexibility as other reverse-mode automatic differ- entiation (AD) techniques, but it can be implemented without any auxiliary data structures besides the function call stack, and it can easily be combined with graph construction and native code generation techniques through forms of multi-stage programming, leading to a highly efficient implementation that combines the per- formance benefits of define-then-run software frameworks such as TensorFlow with the expressiveness of define-by-run frameworks such as PyTorch. -
Learning Maps for Indoor Mobile Robot Navigation
Learning Maps for Indoor Mobile Robot Navigation Sebastian Thrun Arno BÈucken April 1996 CMU-CS-96-121 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 The ®rst author is partly and the second author exclusively af®liated with the Computer Science Department III of the University of Bonn, Germany, where part of this research was carried out. This research is sponsored in part by the National Science Foundation under award IRI-9313367, and by the Wright Laboratory, Aeronautical Systems Center, Air Force Materiel Command, USAF, and the Advanced Research Projects Agency (ARPA) under grant number F33615-93-1-1330. The views and conclusionscontained in this documentare those of the author and should not be interpreted as necessarily representing of®cial policies or endorsements, either expressed or implied, of NSF, Wright Laboratory or the United States Government. Keywords: autonomous robots, exploration, mobile robots, neural networks, occupancy grids, path planning, planning, robot mapping, topological maps Abstract Autonomous robots must be able to learn and maintain models of their environ- ments. Research on mobile robot navigation has produced two major paradigms for mapping indoor environments: grid-based and topological. While grid-based methods produce accurate metric maps, their complexity often prohibits ef®cient planning and problem solving in large-scale indoor environments. Topological maps, on the other hand, can be used much more ef®ciently, yet accurate and consistent topological maps are considerably dif®cult to learn in large-scale envi- ronments. This paper describes an approach that integrates both paradigms: grid-based and topological. Grid-based maps are learned using arti®cial neural networks and Bayesian integration. -
Model Based Systems Engineering Approach to Autonomous Driving
DEGREE PROJECT IN ELECTRICAL ENGINEERING, SECOND CYCLE, 30 CREDITS STOCKHOLM, SWEDEN 2018 Model Based Systems Engineering Approach to Autonomous Driving Application of SysML for trajectory planning of autonomous vehicle SARANGI VEERMANI LEKAMANI KTH ROYAL INSTITUTE OF TECHNOLOGY SCHOOL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE Author Sarangi Veeramani Lekamani [email protected] School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Place for Project Sodertalje, Sweden AVL MTC AB Examiner Ingo Sander School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Supervisor George Ungureanu School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Industrial Supervisor Hakan Sahin AVL MTC AB Abstract Model Based Systems Engineering (MBSE) approach aims at implementing various processes of Systems Engineering (SE) through diagrams that provide different perspectives of the same underlying system. This approach provides a basis that helps develop a complex system in a systematic manner. Thus, this thesis aims at deriving a system model through this approach for the purpose of autonomous driving, specifically focusing on developing the subsystem responsible for generating a feasible trajectory for a miniature vehicle, called AutoCar, to enable it to move towards a goal. The report provides a background on MBSE and System Modeling Language (SysML) which is used for modelling the system. With this background, an MBSE framework for AutoCar is derived and the overall system design is explained. This report further explains the concepts involved in autonomous trajectory planning followed by an introduction to Robot Operating System (ROS) and its application for trajectory planning of the system. The report concludes with a detailed analysis on the benefits of using this approach for developing a system. -
Stuart Russell and Peter Norvig, Artijcial Intelligence: a Modem Approach *
View metadata, citation and similar papers at core.ac.uk brought to you by CORE provided by Elsevier - Publisher Connector Artificial Intelligence ELSEVIER Artificial Intelligence 82 ( 1996) 369-380 Book Review Stuart Russell and Peter Norvig, Artijcial Intelligence: A Modem Approach * Nils J. Nilsson Robotics Laboratory, Department of Computer Science, Stanford University, Stanford, CA 94305, USA 1. Introductory remarks I am obliged to begin this review by confessing a conflict of interest: I am a founding director and a stockholder of a publishing company that competes with the publisher of this book, and I am in the process of writing another textbook on AI. What if Russell and Norvig’s book turns out to be outstanding? Well, it did! Its descriptions are extremely clear and readable; its organization is excellent; its examples are motivating; and its coverage is scholarly and thorough! End of review? No; we will go on for some pages-although not for as many as did Russell and Norvig. In their Preface (p. vii), the authors mention five distinguishing features of their book: Unified presentation of the field, Intelligent agent design, Comprehensive and up-to-date coverage, Equal emphasis on theory and practice, and Understanding through implementation. These features do indeed distinguish the book. I begin by making a few brief, summary comments using the authors’ own criteria as a guide. l Unified presentation of the field and Intelligent agent design. I have previously observed that just as Los Angeles has been called “twelve suburbs in search of a city”, AI might be called “twelve topics in search of a subject”. -
The Dartmouth College Artificial Intelligence Conference: the Next
AI Magazine Volume 27 Number 4 (2006) (© AAAI) Reports continued this earlier work because he became convinced that advances The Dartmouth College could be made with other approaches using computers. Minsky expressed the concern that too many in AI today Artificial Intelligence try to do what is popular and publish only successes. He argued that AI can never be a science until it publishes what fails as well as what succeeds. Conference: Oliver Selfridge highlighted the im- portance of many related areas of re- search before and after the 1956 sum- The Next mer project that helped to propel AI as a field. The development of improved languages and machines was essential. Fifty Years He offered tribute to many early pio- neering activities such as J. C. R. Lick- leiter developing time-sharing, Nat Rochester designing IBM computers, and Frank Rosenblatt working with James Moor perceptrons. Trenchard More was sent to the summer project for two separate weeks by the University of Rochester. Some of the best notes describing the AI project were taken by More, al- though ironically he admitted that he ■ The Dartmouth College Artificial Intelli- Marvin Minsky, Claude Shannon, and never liked the use of “artificial” or gence Conference: The Next 50 Years Nathaniel Rochester for the 1956 “intelligence” as terms for the field. (AI@50) took place July 13–15, 2006. The event, McCarthy wanted, as he ex- Ray Solomonoff said he went to the conference had three objectives: to cele- plained at AI@50, “to nail the flag to brate the Dartmouth Summer Research summer project hoping to convince the mast.” McCarthy is credited for Project, which occurred in 1956; to as- everyone of the importance of ma- coining the phrase “artificial intelli- sess how far AI has progressed; and to chine learning. -
Artificial Intelligence: a Modern Approach (3Rd Edition)
[PDF] Artificial Intelligence: A Modern Approach (3rd Edition) Stuart Russell, Peter Norvig - pdf download free book Free Download Artificial Intelligence: A Modern Approach (3rd Edition) Ebooks Stuart Russell, Peter Norvig, PDF Artificial Intelligence: A Modern Approach (3rd Edition) Popular Download, Artificial Intelligence: A Modern Approach (3rd Edition) Full Collection, Read Best Book Online Artificial Intelligence: A Modern Approach (3rd Edition), Free Download Artificial Intelligence: A Modern Approach (3rd Edition) Full Popular Stuart Russell, Peter Norvig, I Was So Mad Artificial Intelligence: A Modern Approach (3rd Edition) Stuart Russell, Peter Norvig Ebook Download, PDF Artificial Intelligence: A Modern Approach (3rd Edition) Full Collection, full book Artificial Intelligence: A Modern Approach (3rd Edition), online pdf Artificial Intelligence: A Modern Approach (3rd Edition), Download Free Artificial Intelligence: A Modern Approach (3rd Edition) Book, pdf Stuart Russell, Peter Norvig Artificial Intelligence: A Modern Approach (3rd Edition), the book Artificial Intelligence: A Modern Approach (3rd Edition), Download Artificial Intelligence: A Modern Approach (3rd Edition) E-Books, Read Artificial Intelligence: A Modern Approach (3rd Edition) Book Free, Artificial Intelligence: A Modern Approach (3rd Edition) PDF read online, Artificial Intelligence: A Modern Approach (3rd Edition) Ebooks, Artificial Intelligence: A Modern Approach (3rd Edition) Popular Download, Artificial Intelligence: A Modern Approach (3rd Edition) Free Download, Artificial Intelligence: A Modern Approach (3rd Edition) Books Online, Free Download Artificial Intelligence: A Modern Approach (3rd Edition) Books [E-BOOK] Artificial Intelligence: A Modern Approach (3rd Edition) Full eBook, CLICK HERE FOR DOWNLOAD The dorian pencil novels at the end of each chapter featured charts. makes us the meaning of how our trip and unk goes into trouble with others like land. -
Artificial Intelligence
Outline: Introduction to AI Artificial Intelligence N-ways Introduction Introduction to AI - Personal Information and - What is Intelligence? Introduction Background - An Intelligent Entity - The Age of Intelligent Machines Course Outline: - Definitions of AI - Requirements and Expectation - Behaviourist’s View on Intelligent - Module Assessment Machines - Recommended Books - Turing’s Test - Part 1 & 2 - Layout of Course (14 lessons) - History of AI Lecture 1 - Examples of AI systems - Office Hours Course Delivery Methods General Reference for the Course Goals and Objectives of module 2 Course Outline: General Reference for the Course Recommended Books Artificial Intelligence by Patrick Henry Winston AI related information. Whatis.com (Computer Science Dictionary) Logical Foundations of Artificial Intelligence by Michael R. http://whatis.com/search/whatisquery.html Genesereth, Nils J. Nislsson, Nils J. Nilsson General computer-related news sources. Technology Encyclopedia Artificial Intelligence, Luger, Stubblefield http://www.techweb.com/encyclopedia/ General Information Artificial Intelligence : A Modern Approach by Stuart J. Russell, Technology issues. Peter Norvig Computing Dictionary http://wombat.doc.ic.ac.uk/ Artificial Intelligence by Elaine Rich, Kevin Knight (good for All web links in my AI logic, knowledge representation, and search only) website. Webster Dictionary http://work.ucsd.edu:5141/cgi- bin/http_webster 3 4 Goals and Objectives of module Introduction to AI: What is Intelligence? Understand motivation, mechanisms, and potential Intelligence, taken as a whole, consists of of Artificial Intelligence techniques. the following skills:- Balance of breadth of techniques with depth of 1. the ability to reason understanding. 2. the ability to acquire and apply knowledge Conversant with the applicational scope and 3. the ability to manipulate and solution methodologies of AI. -
The `Icebreaker' Challenge for Social Robotics
The ‘Icebreaker’ Challenge for Social Robotics Weronika Sieińska, Nancie Gunson, Christian Dondrup, and Oliver Lemon∗ (w.sieinska;n.gunson;c.dondrup;o.lemon)@hw.ac.uk School of Mathematical and Computer Sciences, Heriot-Watt University Edinburgh, UK ABSTRACT time where they are sitting in a common waiting room, waiting to Loneliness in the elderly is increasingly becoming an issue in mod- be called for their appointments. While waiting, the vast majority ern society. Moreover, the number of older adults is forecast to of patients sit quietly until their next appointment. We aim to increase over the next decades while the number of working-age deploy a robot to this waiting room that can not only give patients adults will decrease. In order to support the healthcare sector, So- information about their next appointment (thus reducing anxiety) cially Assistive Robots (SARs) will become a necessity. We propose and guide them to it, but which also involves them in more general the multi-party conversational robot ‘icebreaker’ challenge for NLG dialogue using open-domain social chit-chat. The challenge we and HRI that is not only aimed at increasing rapport and acceptance propose is to use non-intrusive general social conversation [6] to of robots amongst older adults but also aims to tackle the issue of involve other people, e.g. another patient sitting next to the patient loneliness by encouraging humans to talk with each other. we are already talking to, in the conversation with the robot. Hence we aim to ‘break the ice’ and get both patients to talk together 1 INTRODUCTION in this multi-party interaction. -
Google's Lab of Wildest Dreams
Google’s Lab of Wildest Dreams By CLAIRE CAIN MILLER and NICK BILTON Published: November 13, 2011 MOUNTAIN VIEW, Calif. — In a top-secret lab in an undisclosed Bay Area location where robots run free, the future is being imagined. It’s a place where your refrigerator could be connected to the Internet, so it could order groceries when they ran low. Your dinner plate could post to a social network what you’re eating. Your robot could go to the office while you stay home in your pajamas. And you could, perhaps, take an elevator to outer space. Ramin Rahimian for The New York These are just a few of the dreams being chased at Times Google X, the clandestine lab where Google is Google is said to be considering the tackling a list of 100 shoot-for-the-stars ideas. In manufacture of its driverless cars in the United States. interviews, a dozen people discussed the list; some work at the lab or elsewhere at Google, and some have been briefed on the project. But none would speak for attribution because Google is so secretive about the effort that many employees do not even know the lab exists. Although most of the ideas on the list are in the conceptual stage, nowhere near reality, two people briefed on the project said one product would be released by the end of the year, although they would not say what it was. “They’re pretty far out in front right now,” said Rodney Brooks, a professor emeritus at M.I.T.’s computer science and artificial intelligence lab and founder of Heartland Robotics. -
Apply Artificial Intelligence to Get Value AI2V 101 by Alexandre Dietrich
AI2V Apply Artificial Intelligence to get Value AI2V 101 By Alexandre Dietrich AlexD.ai What is AI ? AlexD.ai What is AI ? Google search: “Artificial Intelligence definition” Encyclopaedia Brittanica: Dictionary: Artificial intelligence (AI), the ability of a digital computer the theory and development of computer systems or computer-controlled robot to perform tasks commonly able to perform tasks that normally require human associated with intelligent beings. The term is frequently intelligence, such as visual perception, speech applied to the project of developing systems endowed with recognition, decision-making, and translation the intellectual processes characteristic of humans, such as between languages. the ability to reason, discover meaning, generalize, or learn from past experience. Stanford University – Computer Science Department: Q. What is artificial intelligence? A. It is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable. Mckinsey & Company: Artificial intelligence: A definition AI is typically defined as the ability of a machine to perform cognitive functions we associate with human minds, such as perceiving, reasoning, learning, and problem solving. Examples of technologies that enable AI to solve business problems are robotics and autonomous vehicles, computer vision, language, virtual agents, and machine