simulation@uflorida.cis.ufl.edu (Moderator: Paul Fishwick) (12/19/89)
Volume: 13, Issue: 1, Tue Dec 19 09:22:12 EST 1989 +----------------+ | TODAY'S TOPICS | +----------------+ (1) Yet Another GVT Algorithm (2) RE: Overview of DMOD (3) Discrete Event Simulation (4) Wang Institute Conference * Moderator: Paul Fishwick, Univ. of Florida * Send topical mail to: simulation@bikini.cis.ufl.edu OR post to comp.simulation via USENET * Archives available via FTP to bikini.cis.ufl.edu, login as 'ftp', use your last name as the password, change directory to pub/simdigest. * Simulation Tools available by doing above and changing the directory to pub/simdigest/tools. ----------------------------------------------------------------------------- Via: UK.AC.EX.CS; 14 DEC 89 0:34:35 GMT From: Ming Chiang Xu <mxu%CS.EXETER.AC.UK@nervm.nerdc.ufl.edu> Date: Thu, 14 Dec 89 00:36:24 GMT To: simulation@BIKINI.CIS.UFL.EDU, mxu@CS.EXETER.AC.UK Subject: Yet Another GVT Algorithm Usually, GVT (Global Virtual Time) can be computed by determining the minimum of: (a) all local clocks (b) the send times of all messages "in transit" (c) the send times of all messages in input queues which have not yet been processed. It always horrifies me to think that I have to go through all this hustle only to calculate a "imprecise" GVT. Therefore, for ages, I have had a negative attitude towards implementing a "decent" GVT finding algorithm. Instead, I only looked at the all the local clocks and circulate a token carrying a minimum local clock value several times before discarding the old "dead" states. Sometimes, it worries me, as I told Jason Lin, that this way is not robust. I can be in real trouble if I don't get it right. Incidentally, I found the applicability of the Dijkstra termination detection algorithm in finding a GVT, or rather, bidding a GVT. First of all, circulate a token to obtain the minimum local clock value. This value may not be GVT right now but may later on be so. We therefore apply the Dijkstra Algorithm to detect when it is so. The following discussion assumes that processes are organised as a ring (or, there is a Harmilton circle in the process connection graph). One process is a token master process and the rest are token slave processes. The master and slaves circulate a token continuously. This contains two fields: colour and time. The time represents a proposed value for the GVT. The proposed GVT can be the minimum clock value (or plus a predefined positive value). First round of the circulation only notifies the processes of the proposed GVT and the token is only passed when a process currently holding the token has processed all the messages with send times before the proposed GVT. A process is coloured white after it passes the token to its successor. A white process becomes black when it receives a message with a send time before the proposed GVT. A black process passes a black token to its successor whereas the white process does not change the colour of token. This is where the Dijkstra Algorithm comes in. The idea is to circulate a token which is initially white and at the end of the second circuit, if the colour of the token is white, then the message before the proposed GVT can be discarded. Otherwise start another circulation until the colour of token at the end of the circuit is white. In the context of general process communication structure, there is also another version of Dijkstra algorithm available. The algorithm does not generate lots of messages and in fact it is not computational intensive. Moreover, it is flexible. The proposed GVT can also be elected, if you like, from the processes whose message queue exceeds a threshold value. This means that the states may not be discarded regularly. As mentioned earlier, I do not know enougth about other GVT finding algorithms to make more credits on mine. Therefore... If anyone have any information or experience on calculating the GVT and is willing to let me know, please resort to the following addresses: Ming Q. Xu Dept. of Computer Science University of Exeter Prince of Wales Road Exeter EX4 4PT England. U.K. Email: mxu@uk.ac.ex.cs ------------------------------ Posted-Date: Thu, 14 Dec 89 10:21:58 CST Date: Thu, 14 Dec 89 10:21:58 CST From: steve@titan.tsd.arlut.utexas.edu (Steve Glicker) To: simulation@bikini.cis.ufl.edu Subject: Re: Overview of DMOD This is a response on the "Overview of DMOD" article submitted by Sanjai Narain. Sorry about the slow response time -- I have been busy with a simulator. I would like to get clarification on some terminology and several points in the article: As I understand it, events are treated as data and rules are used to to represent causality relations (derive state information and schedule events as well as present state and event information to the user). I assume that instances of simulated entities (e.g., machines and materials) are represented as data which contain no state information. All historical information is saved (all *events* canceled or not and simulated entities) and simulation is driven by events and possibly limited by some time constraint. Please correct me if I am wrong. > DMOD is a first step in our attempts to achieve our goals. It is based > upon the following fundamental assumption: > > If all event occurrences in a system till time T are known, the > state of the system can be computed at any point of time till T. > > Thus, simulation is regarded as computation of event occurrences. ... Viewing DES as the computation of events, IMHO, is accepted and requires no assumption. I do think that there is a problem with the way this assumption is stated. Simulation models that have state usually require an initial state before simulation can proceed. Some default initial state must be assumed (consider a simulation model of a closed-system). I think of an event occurrence as something that takes place at a point in time (or a simulated something that takes place at a point in simulation time). I don't think of a canceled event (a descheduled event) as one that occurred. I get the impression the term "event occurrence" is used to indicate that and event record (in terms of an event record for a next- event or time queue) is created. With clarification and/or confirmation on these items I should be able to contribute some more comments. Steve Glicker (steve@titan.tsd.arlut.utexas.edu) ------------------------------ To: simulation-maillist@ufl.edu Cc: narain%pluto@rand.org Date: Mon, 18 Dec 89 13:21:27 PST From: narain%pluto@rand.org The event scheduling view of the discrete-event technique is generally intended to simulate discrete systems, i.e. those whose state changes only at discrete instants of time. When continuous parameters are involved, e.g. position, temperature, voltage, pressure, the technique is suitably extended. However, sometimes the extension is not obvious for situations such as the one defined by the following rules: If a chip is put into the furnace at time T then it is cooked at time T+300, provided the temperature of the furnace never drops below 700 at any point of time between T and T+300. Temperature of furnace at time 0 is 800. When furnace is switched off, temperature drop is given by the continuous function f(t). Similarly, when furnace is switched on, temperature rise is given by the continuous function g(t). Now, suppose an event "chip put into furnace" occurs at time 0. By the discrete-event technique, we would schedule the event "chip cooked" for time 300. Now, suppose an event "furnace switched off" occurs at time 100. Question: Do we unschedule "chip cooked" for time 300? If we do unschedule it, then as the temperature falls gradually from 800, "furnace switched on" may occur before temperature has fallen to below 700. So, the unscheduling condition may never actually arise. However, "chip cooked" would not be recorded as occurring at time 300, as it should be. If we do not unschedule it, then the temperature could eventually fall below 700 and "chip cooked" would be erroneously recorded as occurring at 300. The problem arises because in unscheduling events we try to do "look ahead" i.e. determine, given the current state, whether a scheduled event will occur. The implicit assumption is that state changes occur only at event boundaries. However, when continuous parameters are involved, state changes may also occur between event boundaries and give rise to unscheduling conditions. Monitoring for such conditions can be quite hard. This problem does not arise in DMOD as it is based upon "looking back". If an event E is predicted to occur at time T then a condition C is associated with it which is defined over the entire past of T. When simulation time reaches T the entire past of T is known, so C can be evaluated. If true, E is recorded as occurring, otherwise it is discarded. As DMOD focusses on computing histories, not states, a convenient handle on the past of T is the history up to T. Comments are greatly appreciated. Sanjai Narain RAND ------------------------------ Date: Thu, 14 Dec 89 14:05:11 EST From: mike@bucasb.BU.EDU (Michael Cohen) To: ai-chi@LLL-LCC.LLNL.GOV, ailist@AI.AI.MIT.EDU, vision-list@ADS.COM, epsynet@uhupvm1.bitnet, neuron@hplabs.hp.com, self-org@mc.lcs.mit.edu, arpanet-bboards@mc.lcs.mit.edu, parsym@sumex-aim.stanford.edu, physics@mc.lcs.mit.edu, soft-eng@xx.lcs.mit.edu, TheoryNet@ibm.com, connectionists@RI.CMU.EDU, info-futures@CS.BU.EDU, dynsys-l@uncvm1.bitnet, biotech@umdc.bitnet, mcmi!denny, human-nets@aramis.rutgers.edu, optics-l@taunivm.bitnet, simulation@ufl.edu Subject: WANG INSTITUTE CONFERENCE BOSTON UNIVERSITY, A WORLD LEADER IN NEURAL NETWORK RESEARCH AND TECHNOLOGY, PRESENTS TWO MAJOR SCIENTIFIC EVENTS: MAY 6--11, 1990 NEURAL NETWORKS: FROM FOUNDATIONS TO APPLICATIONS A self-contained systematic course by leading neural architects. MAY 11--13, 1990 NEURAL NETWORKS FOR AUTOMATIC TARGET RECOGNITION An international research conference presenting INVITED and CONTRIBUTED papers, herewith solicited, on one of the most active research topics in science and technology today. SPONSORED BY THE CENTER FOR ADAPTIVE SYSTEMS, THE GRADUATE PROGRAM IN COGNITIVE AND NEURAL SYSTEMS, AND THE WANG INSTITUTE OF BOSTON UNIVERSITY WITH PARTIAL SUPPORT FROM THE AIR FORCE OFFICE OF SCIENTIFIC RESEARCH ----------------------------------------------------------------------------- CALL FOR PAPERS --------------- NEURAL NETWORKS FOR AUTOMATIC TARGET RECOGNITION MAY 11--13, 1990 This research conference at the cutting edge of neural network science and technology will bring together leading experts in academe, government, and industry to present their latest results on automatic target recognition in invited lectures and contributed posters. Automatic target recognition is a key process in systems designed for vision and image processing, speech and time series prediction, adaptive pattern recognition, and adaptive sensory-motor control and robotics. It is one of the areas emphasized by the DARPA Neural Networks Program, and has attracted intense research activity around the world. Invited lecturers include: JOE BROWN, Martin Marietta, "Multi-Sensor ATR using Neural Nets" GAIL CARPENTER, Boston University, "Target Recognition by Adaptive Resonance: ART for ATR" NABIL FARHAT, University of Pennsylvania, "Bifurcating Networks for Target Recognition" STEPHEN GROSSBERG, Boston University, "Recent Results on Self-Organizing ATR Networks" ROBERT HECHT-NIELSEN, HNC, "Spatiotemporal Attention Focusing by Expectation Feedback" KEN JOHNSON, Hughes Aircraft, "The Application of Neural Networks to the Acquisition and Tracking of Maneuvering Tactical Targets in High Clutter IR Imagery" PAUL KOLODZY, MIT Lincoln Laboratory, "A Multi-Dimensional ATR System" MICHAEL KUPERSTEIN, Neurogen, "Adaptive Sensory-Motor Coordination using the INFANT Controller" YANN LECUN, AT&T Bell Labs, "Structured Back Propagation Networks for Handwriting Recognition" CHRISTOPHER SCOFIELD, Nestor, "Neural Network Automatic Target Recognition by Active and Passive Sonar Signals" STEVEN SIMMES, Science Applications International Co., "Massively Parallel Approaches to Automatic Target Recognition" ALEX WAIBEL, Carnegie Mellon University, "Patterns, Sequences and Variability: Advances in Connectionist Speech Recognition" ALLEN WAXMAN, MIT Lincoln Laboratory, "Invariant Learning and Recognition of 3D Objects from Temporal View Sequences" FRED WEINGARD, Booz-Allen and Hamilton, "Current Status and Results of Two Major Government Programs in Neural Network-Based ATR" BARBARA YOON, DARPA, "DARPA Artificial Neural Networks Technology Program: Automatic Target Recognition" ------------------------------------------------------ CALL FOR PAPERS---ATR POSTER SESSION: A featured poster session on ATR neural network research will be held on May 12, 1990. Attendees who wish to present a poster should submit 3 copies of an extended abstract (1 single-spaced page), postmarked by March 1, 1990, for refereeing. Include with the abstract the name, address, and telephone number of the corresponding author. Mail to: ATR Poster Session, Neural Networks Conference, Wang Institute of Boston University, 72 Tyng Road, Tyngsboro, MA 01879. Authors will be informed of abstract acceptance by March 31, 1990. SITE: The Wang Institute possesses excellent conference facilities on a beautiful 220-acre rustic setting. It is easily reached from Boston's Logan Airport and Route 128. REGISTRATION FEE: Regular attendee--$90; full-time student--$70. Registration fee includes admission to all lectures and poster session, one reception, two continental breakfasts, one lunch, one dinner, daily morning and afternoon coffee service. STUDENTS: Read below about FELLOWSHIP support. REGISTRATION: To register by telephone with VISA or MasterCard call (508) 649-9731 between 9:00AM--5:00PM (EST). To register by FAX, fill out the registration form and FAX back to (508) 649-6926. To register by mail, complete the registration form and mail with your full form of payment as directed. Make check payable in U.S. dollars to "Boston University". See below for Registration Form. To register by electronic mail, use the address "rosenber@bu-tyng.bu.edu". On-site registration on a space-available basis will take place from 1:00--5:00PM on Friday, May 11. A RECEPTION will be held from 3:00--5:00PM on Friday, May 11. LECTURES begin at 5:00PM on Friday, May 11 and conclude at 1:00PM on Sunday, May 13. ------------------------------------------------------------------------------ NEURAL NETWORKS: FROM FOUNDATIONS TO APPLICATIONS MAY 6--11, 1989 This in-depth, systematic, 5-day course is based upon the world's leading graduate curriculum in the technology, computation, mathematics, and biology of neural networks. Developed at the Center for Adaptive Systems (CAS) and the Graduate Program in Cognitive and Neural Systems (CNS) of Boston University, twenty-eight hours of the course will be taught by six CAS/CNS faculty. Three distinguished guest lecturers will present eight hours of the course. COURSE OUTLINE -------------- MAY 7, 1990 ----------- MORNING SESSION (PROFESSOR GROSSBERG) HISTORICAL OVERVIEW: Introduction to the binary, linear, and continuous-nonlinear streams of neural network research: McCulloch-Pitts, Rosenblatt, von Neumann; Anderson, Kohonen, Widrow; Hodgkin-Huxley, Hartline-Ratliff, Grossberg. CONTENT ADDRESSABLE MEMORY: Classification and analysis of neural network models for absolutely stable CAM. Models include: Cohen-Grossberg, additive, shunting, Brain-State-In-A-Box, Hopfield, Boltzmann Machine, McCulloch-Pitts, masking field, bidirectional associative memory. COMPETITIVE DECISION MAKING: Analysis of asynchronous variable-load parallel processing by shunting competitive networks; solution of noise-saturation dilemma; classification of feedforward networks: automatic gain control, ratio processing, Weber law, total activity normalization, noise suppression, pattern matching, edge detection, brightness constancy and contrast, automatic compensation for variable illumination or other background energy distortions; classification of feedback networks: influence of nonlinear feedback signals, notably sigmoid signals, on pattern transformation and memory storage, winner-take-all choices, partial memory compression, tunable filtering, quantization and normalization of total activity, emergent boundary segmentation; method of jumps for classifying globally consistent and inconsistent competitive decision schemes. ASSOCIATIVE LEARNING: Derivation of associative equations for short-term memory and long-term memory. Overview and analysis of associative outstars, instars, computational maps, avalanches, counterpropagation nets, adaptive bidrectional associative memories. Analysis of unbiased associative pattern learning by asynchronous parallel sampling channels; classification of associative learning laws. AFTERNOON SESSION (PROFESSORS JORDAN AND MINGOLLA) COMBINATORIAL OPTIMIZATION PERCEPTRONS: Adeline, Madeline, delta rule, gradient descent, adaptive statistical predictor, nonlinear separability. INTRODUCTION TO BACK PROPAGATION: Supervised learning of multidimensional nonlinear maps, NETtalk, image compression, robotic control. RECENT DEVELOPMENTS OF BACK PROPAGATION: This two-hour guest tutorial lecture will provide a systematic review of recent developments of the back propagation learning network, especially focussing on recurrent back propagation variations and applications to outstanding technological problems. EVENING SESSION: DISCUSSIONS WITH TUTORS MAY 8, 1990 ----------- MORNING SESSION (PROFESSORS CARPENTER AND GROSSBERG) ADAPTIVE PATTERN RECOGNITION: Adaptive filtering; contrast enhancement; competitive learning of recognition categories; adaptive vector quantization; self-organizing computational maps; statistical properties of adaptive weights; learning stability and causes of instability. INTRODUCTION TO ADAPTIVE RESONANCE THEORY: Absolutely stable recognition learning, role of learned top-down expectations; attentional priming; matching by 2/3 Rule; adaptive search; self-controlled hypothesis testing; direct access to globally optimal recognition code; control of categorical coarseness by attentional vigilance; comparison with relevant behavioral and brain data to emphasize biological basis of ART computations. ANALYSIS OF ART 1: Computational analysis of ART 1 architecture for self-organized real-time hypothesis testing, learning, and recognition of arbitrary sequences of binary input patterns. AFTERNOON SESSION (PROFESSOR CARPENTER) ANALYSIS OF ART 2: Computational analysis of ART 2 architecture for self-organized real-time hypothesis testing, learning, and recognition for arbitrary sequences of analog or binary input patterns. ANALYSIS OF ART 3: Computational analysis of ART 3 architecture for self-organized real-time hypothesis testing, learning, and recognition within distributed network hierarchies; role of chemical transmitter dynamics in forming a memory representation distinct from short-term memory and long-term memory; relationships to brain data concerning neuromodulators and synergetic ionic and transmitter interactions. SELF-ORGANIZATION OF INVARIANT PATTERN RECOGNITION CODES: Computational analysis of self-organizing ART architectures for recognizing noisy imagery undergoing changes in position, rotation, and size. NEOCOGNITION: Recognition and completion of images by hierarchical bottom-up filtering and top-down attentive feedback. EVENING SESSION: DISCUSSIONS WITH TUTORS MAY 9, 1990 ----------- MORNING SESSION (PROFESSORS GROSSBERG & MINGOLLA) VISION AND IMAGE PROCESSING: Introduction to Boundary Contour System for emergent segmentation and Feature Contour System for filling-in after compensation for variable illumination; image compression, orthogonalization, and reconstruction; multidimensional filtering, multiplexing, and fusion; coherent boundary detection, regularization, self-scaling, and completion; compensation for variable illumination sources, including artificial sensors (infrared sensors, laser radars); filling-in of surface color and form; 3-D form from shading, texture, stereo, and motion; parallel processing of static form and moving form; motion capture and induced motion; synthesis of static form and motion form representations. AFTERNOON SESSION (PROFESSORS BULLOCK, COHEN, & GROSSBERG) ADAPTIVE SENSORY-MOTOR CONTROL AND ROBOTICS: Overview of recent progress in adaptive sensory-motor control and related robotics research. Reaching to, grasping, and transporting objects of variable mass and form under visual guidance in a cluttered environment will be used as a target behavioral competence to clarify subproblems of real-time adaptive sensory-motor control. The balance of the tutorial will be spent detailing neural network modules that solve various subproblems. Topics include: Self-organizing networks for real-time control of eye movements, arm movements, and eye-arm coordination; learning of invariant body-centered target position maps; learning of intermodal associative maps; real-time trajectory formation; adaptive vector encoders; circular reactions between action and sensory feedback; adaptive control of variable speed movements; varieties of error signals; supportive behavioral and neural data; inverse kinematics; automatic compensation for unexpected perturbations; independent adaptive control of force and position; adaptive gain control by cerebellar learning; position-dependent sampling from spatial maps; predictive motor planning and execution. SPEECH PERCEPTION AND PRODUCTION: Hidden Markov models; self-organization of speech perception and production codes; eighth nerve Average Localized Synchrony Response; phoneme recognition by back propagation, time delay networks, and vector quantization. MAY 10, 1990 ------------ MORNING SESSION (PROFESSORS COHEN, GROSSBERG, & MERRILL) SPEECH PERCEPTION AND PRODUCTION: Disambiguation of coarticulated vowels and consonants; dynamics of working memory; multiple-scale adaptive coding by masking fields; categorical perception; phonemic restoration; contextual disambiguation of speech tokens; resonant completion and grouping of noisy variable-rate speech streams. REINFORCEMENT LEARNING AND PREDICTION: Recognition learning, reinforcement learning, and recall learning are the 3 R's of neural network learning. Reinforcement learning clarifies how external events interact with internal organismic requirements to trigger learning processes capable of focussing attention upon and generating appropriate actions towards motivationally desired goals. A neural network model will be derived to show how reinforcement learning and recall learning can self-organize in response to asynchronous series of significant and irrelevant events. These mechanisms also control selective forgetting of memories that are no longer predictive, adaptive timing of behavioral responses, and self-organization of goal directed problem solvers. AFTERNOON SESSION (PROFESSORS GROSSBERG & MERRILL AND DR. HECHT-NIELSEN) REINFORCEMENT LEARNING AND PREDICTION: Analysis of drive representations, adaptive critics, conditioned reinforcers, role of motivational feedback in focusing attention on predictive data; attentional blocking and unblocking; adaptively timed problem solving; synthesis of perception, recognition, reinforcement, recall, and robotics mechanisms into a total neural architecture; relationship to data about hypothalamus, hippocampus, neocortex, and related brain regions. RECENT DEVELOPMENTS IN THE NEUROCOMPUTER INDUSTRY: This two-hour guest tutorial will provide an overview of the growth and prospects of the burgeoning neurocomputer industry by one of its most important leaders. EVENING SESSION: DISCUSSIONS WITH TUTORS MAY 11, 1990 ------------ MORNING SESSION (DR. FAGGIN) VLSI IMPLEMENTATION OF NEURAL NETWORKS: This is a four-hour self-contained tutorial on the application and development of VLSI techniques for creating compact real-time chips embodying neural network designs for applications in technology. Review of neural networks from a hardware implementation perspective; hardware requirements and alternatives; dedicated digital implementation of neural networks; neuromorphic design methodology using VLSI CMOS technology; applications and performance of neuromorphic implementations; comparison of neuromorphic and digital hardware; future prospectus. ---------------------------------------------------------------------------- COURSE FACULTY FROM BOSTON UNIVERSITY ------------------------------------- STEPHEN GROSSBERG, Wang Professor of CNS, as well as Professor of Mathematics, Psychology, and Biomedical Engineering, is one of the world's leading neural network pioneers and most versatile neural architects; Founder and 1988 President of the International Neural Network Society (INNS); Founder and Co-Editor-in-Chief of the INNS journal "Neural Networks"; an editor of the journals "Neural Computation", "Cognitive Science", and "IEEE Expert"; Founder and Director of the Center for Adaptive Systems; General Chairman of the 1987 IEEE First International Conference on Neural Networks (ICNN); Chief Scientist of Hecht-Nielsen Neurocomputer Company (HNC); and one of the four technical consultants to the national DARPA Neural Network Study. He is author of 200 articles and books about neural networks, including "Neural Networks and Natural Intelligence" (MIT Press, 1988), "Neural Dynamics of Adaptive Sensory-Motor Control" (with Michael Kuperstein, Pergamon Press, 1989), "The Adaptive Brain, Volumes I and II" (Elsevier/North-Holland, 1987), "Studies of Mind and Brain" (Reidel Press, 1982), and the forthcoming "Pattern Recognition by Self-Organizing Neural Networks" (with Gail Carpenter). GAIL CARPENTER is Professor of Mathematics and CNS; Co-Director of the CNS Graduate Program; 1989 Vice President of the International Neural Network Society (INNS); Organization Chairman of the 1988 INNS annual meeting; Session Chairman at the 1989 and 1990 IEEE/INNS International Joint Conference on Neural Networks (IJCNN); one of four technical consultants to the national DARPA Neural Network Study; editor of the journals "Neural Networks", "Neural Computation", and "Neural Network Review"; and a member of the scientific advisory board of HNC. A leading neural architect, Carpenter is especially well-known for her seminal work on developing the adaptive resonance theory architectures (ART 1, ART 2, ART 3) for adaptive pattern recognition. MICHAEL COHEN, Associate Professor of Computer Science and CNS, is a leading architect of neural networks for content addressable memory (Cohen-Grossberg model), vision (Feature Contour System), and speech (Masking Fields); editor of "Neural Networks"; Session Chairman at the 1987 ICNN, and the 1989 IJCNN; and member of the DARPA Neural Network Study panel on Simulation/Emulation Tools and Techniques. ENNIO MINGOLLA, Assistant Professor of Psychology and CNS, is holder of one of the first patented neural network architectures for vision and image processing (Boundary Contour System); Co-Organizer of the 3rd Workshop on Human and Machine Vision in 1985; editor of the journals "Neural Networks" and "Ecological Psychology"; member of the DARPA Neural Network Study panel of Adaptive Knowledge Processing; consultant to E.I. duPont de Nemours, Inc.; Session Chairman for vision and image processing at the 1987 ICNN, and the 1988 INNS meetings. DANIEL BULLOCK, Assistant Professor of Psychology and CNS, is developer of neural network models for real-time adaptive sensory-motor control of arm movements and eye-arm coordination, notably the VITE and FLETE models for adaptive control of multi-joint trajectories; editor of "Neural Networks"; Session Chairman for adaptive sensory-motor control and robotics at the 1987 ICNN and the 1988 INNS meetings; invited speaker at the 1990 IJCNN. JOHN MERRILL, Assistant Professor of Mathematics and CNS, is developing neural network models for adaptive pattern recognition, speech recognition, reinforcement learning, and adaptive timing in problem solving behavior, after having received his Ph.D. in mathematics from the University of Wisconsin at Madison, and completing postdoctoral research in computer science and linguistics at Indiana University. GUEST LECTURERS --------------- FEDERICO FAGGIN is co-founder and president of Synaptics, Inc. Dr. Faggin developed the Silicon Gate Technology at Fairchild Semiconductor. He also designed the first commercial circuit using Silicon Gate Technology: the 3708, an 8-bit analog multiplexer. At Intel Corporation he was responsible for designing what was to become the first microprocessor---the 4000 family, also called MCS-4. He and Hal Feeney designed the 8008, the first 8-bit microprocessor introduced in 1972, and later Faggin conceived the 8080 and with M. Shima designed it. The 8080 was the first high-performance 8-bit microprocessor. At Zilog Inc., Faggin conceived the Z80 microprocessor family and directed the design of the Z80 CPU. Faggin also started Cygnet Technologies, which developed a voice and data communication peripheral for the personal computer. In 1986 Faggin co-founded Synaptics Inc., a company dedicated to the creation of a new type of VLSI hardware for artificial neural networks and other machine intelligence applications. Faggin is the recipient of the 1988 Marconi Fellowship Award for his contributions to the birth of the microprocessor. ROBERT HECHT-NIELSEN is co-founder and chairman of the Board of Directors of Hecht-Nielsen Neurocomputer Corporation (HNC), a pioneer in neurocomputer technology and the application of neural networks, and a recognized leader in the field. Prior to the formation of HNC, he founded and managed the neurocomputer development and neural network applications at TRW (1983--1986) and Motorola (1979--1983). He has been active in neural network technology and neurocomputers since 1961 and earned his Ph.D. in mathematics in 1974. He is currently a visiting lecturer in the Electrical Engineering Department at the University of California at San Diego, and is the author of influential technical reports and papers on neurocomputers, neural networks, pattern recognition, signal processing algorithms, and artificial intelligence. MICHAEL JORDAN is an Assistant Professor of Brain and Cognitive Sciences at MIT. One of the key developers of the recurrent back propagation algorithms, Professor Jordan's research is concerned with learning in recurrent networks and with the use of networks as forward models in planning and control. His interest in interdisciplinary research on neural networks is founded in his training for a Bachelors degree in Psychology, a Masters degree in Mathematics, and a Ph.D. in Cognitive Science from the University of California at San Diego. He was a postdoctoral researcher in Computer Science at the University of Massachusetts at Amherst before assuming his present position at MIT. ---------------------------------------------------------- REGISTRATION FEE: Regular attendee--$950; full-time student--$250. Registration fee includes five days of tutorials, course notebooks, one reception, five continental breakfasts, five lunches, four dinners, daily morning and afternoon coffee service, evening discussion sessions with leading neural architects. REGISTRATION: To register by telephone with VISA or MasterCard call (508) 649-9731 between 9:00AM--5:00PM (EST). To register by FAX, fill out the registration form and FAX back to (508) 649-6926. To register by mail, complete the registration form and mail with you full form of payment as directed. Make check payable in U.S. dollars to "Boston University". See below for Registration Form. To register by electronic mail, use the address "rosenber@bu-tyng.bu.edu". On-site registration on a space-available basis will take place from 2:00--7:00PM on Sunday, May 6 and from 7:00--8:00AM on Monday, May 7, 1990. A RECEPTION will be held from 4:00--7:00PM on Sunday, May 6. LECTURES begin at 8:00AM on Monday, May 7 and conclude at 12:30PM on Friday, May 11. STUDENT FELLOWSHIPS supporting travel, registration, and lodging for the Course and the Research Conference are available to full-time graduate students in a PhD program. Applications must be postmarked by March 1, 1990. Send curriculum vitae, a one-page essay describing your interest in neural networks, and a letter from a faculty advisor to: Student Fellowships, Neural Networks Course, Wang Institute of Boston University, 72 Tyng Road, Tyngsboro, MA 01879. CNS FELLOWSHIP FUND: Net revenues from the course will endow fellowships for Ph.D. candidates in the CNS Graduate Program. Corporate and individual gifts to endow CNS Fellowships are also welcome. Please write: Cognitive and Neural Systems Fellowship Fund, Center for Adaptive Systems, Boston University, 111 Cummington Street, Boston, MA 02215. ------------------------------------------------------------------------------ REGISTRATION FOR COURSE AND RESEARCH CONFERENCE Course: Neural Network Foundations and Applications, May 6--11, 1990 Research Conference: Neural Networks for Automatic Target Recognition, May 11--13, 1990 NAME: _________________________________________________________________ ORGANIZATION (for badge): _____________________________________________ MAILING ADDRESS: ______________________________________________________ ______________________________________________________ CITY/STATE/COUNTRY: ___________________________________________________ POSTAL/ZIP CODE: ______________________________________________________ TELEPHONE(S): _________________________________________________________ COURSE RESEARCH CONFERENCE ------ ------------------- [ ] regular attendee $950 [ ] regular attendee $90 [ ] full-time student $250 [ ] full-time student $70 (limited number of spaces) (limited number of spaces) [ ] Gift to CNS Fellowship Fund TOTAL PAYMENT: $________ FORM OF PAYMENT: [ ] check or money order (payable in U.S. dollars to Boston University) [ ] VISA [ ] MasterCard Card Number: ______________________________________________ Expiration Date: ______________________________________________ Signature: ______________________________________________ Please complete and mail to: Neural Networks Wang Institute of Boston University 72 Tyng Road Tyngsboro, MA 01879 USA To register by telephone, call: (508) 649-9731. HOTEL RESERVATIONS: Room blocks have been reserved at 3 hotels near the Wang Institute. Hotel names, rates, and telephone numbers are listed below. A shuttle bus will take attendees to and from the hotels for the Course and Research Conference. Attendees should make their own reservations by calling the hotel. The special conference rate applies only if you mention the name and dates of the meeting when making the reservations. Sheraton Tara Red Roof Inn Stonehedge Inn Nashua, NH Nashua, NH Tyngsboro, MA (603) 888-9970 (603) 888-1893 (508) 649-4342 $70/night+tax $39.95/night+tax $89/night+tax The hotels in Nashua are located approximately 5 miles from the Wang Institute. A shuttle bus will be provided. ------------------------------------------------------------------------------- ------------------------------ END OF SIMULATION DIGEST ************************