neuron-request@HPLMS2.HPL.HP.COM ("Neuron-Digest Moderator Peter Marvit") (04/02/91)
Neuron Digest Monday, 1 Apr 1991 Volume 7 : Issue 16 Today's Topics: Genetic algorithms + fractals or L-systems? USPS address for alternate site Rigorous results on Fault Tolerance and Robustness (Are there any?) learned discriminations based upon intensity Utah's First Annual Cognitive Science Lecture Cognitive Science at Birmingham POSITIONS IN NEURAL NETWORKS Johns Hopkins' search for applications to aid disabled Postdoc at U of Edinburgh Summer/WInter Fellowships at DEC/Europe AI and NN: industrial applications Applications of ANN in Finance and Banking Boolean Models(GSN) Send submissions, questions, address maintenance and requests for old issues to "neuron-request@hplabs.hp.com" or "{any backbone,uunet}!hplabs!neuron-request" Use "ftp" to get old issues from hplpm.hpl.hp.com (15.255.176.205). ------------------------------------------------------------ Subject: Genetic algorithms + fractals or L-systems? From: Kingsley Morse <kingsley@hpwrce.hp.com> Date: Mon, 25 Mar 91 19:34:47 -0800 Is anyone out there mixing genetic algorithms with fractals or L-systems? ------------------------------ Subject: USPS address for alternate site From: elsberry@evax.uta.edu (Wesley R Elsberry) Date: Wed, 27 Mar 91 00:02:02 -0500 Re: Announcement in ND V7 I:15 In informing Neuron Digest of the existence of Central Neural System BBS, I managed to omit a critical piece of information for those wishing to send disks for obtaining files: a snail-mail address. Here it is, with my apologies for the inconvenience this mistake may have caused: Wesley R. Elsberry Sysop, Central Neural System BBS 528 Chambers Creek Dr. S. Everman, TX 76140 [[ Editor's Note: Thanks again, Wesley! -PM ]] ------------------------------ Subject: Rigorous results on Fault Tolerance and Robustness (Are there any?) From: Dario Ringach <dario%techunix.bitnet@TAUNIVM.TAU.AC.IL> Date: Thu, 28 Mar 91 07:43:25 +0200 It is usually claimed that one of the advantages of networks of simple computing elements is their fault tolerance (or robustness) to connectivity and node failures. However, I find it difficult to find *rigorous* results on this topic so far. Can anyone provide me any references on this subject? Thanks in advance. -Dario Dario Ringach Technion, Israel Institute of Technology Dept. of Electrical Engineering, 32000 Haifa, Israel dario@techunix.bitnet | dario@techunix.technion.ac.il ------------------------------ Subject: learned discriminations based upon intensity From: Jonathan Schull <J_SCHULL@ACC.HAVERFORD.EDU> Date: Fri, 29 Mar 91 17:42:00 -0500 We want to build a neural net which takes the activation level of one sensory neuron as the indicator of the intensity of an external stimulus, and learns to make different responses depending upon the intensity. Does anyone know the standard architecture and learning rule for this kind of problem? [[ Editor's Note: This may be my misunderstanding, but just defining an "input" node as a sensory neuron does the job. That is, the level of the stimulus becomes, by definition in a simple model, the output of that first node. Readers, can you enlighten me as to the distincion here? -PM ]] ------------------------------ Subject: Utah's First Annual Cognitive Science Lecture From: Jerome Soller <soller@cs.utah.edu> Date: Mon, 18 Mar 91 22:55:06 -0700 The speaker at the First Annual Utah Cognitive Science Lecture is Dr. Andreas Andreou of the Johns Hopkins University Electrical Engineering Department. His topic is "A Physical Model of the Retina in Analog VLSI That Explains Optical Illusions". This provides a contrast to Dr. Carver Mead of Caltech, who spoke earlier this year in Utah at the Computer Science Department's Annual Organick Lecture. The time and date of the First Annual Cognitive Science Lecture will be Tuesday, April 2nd, 4:00 P.M. The room will be 101 EMCB(next to the Merrill Engineering Building), University of Utah, Salt Lake City, Utah. A small reception(refreshments) will be available. This event is cosponsored by the Sigma Xi Resarch Fraternity. Dr. Dick Normann, Dr. Ken Horch, Dr. Dick Burgess, and Dr. Phil Hammond were extremely helpful in organizing this event. For more information on this event and other Cognitive Science related events in the state of Utah, contact me (801)-581-4710 or by e-mail(preferred) (soller@cs.utah.edu) . We have an 130 person electronic mailing list within the state of Utah announcing these kind of events. We are also finishing up this year's edition of the Utah Cognitive Science Information Guide, which contains 80 faculty, 60 graduate students, 60 industry representatives, 32 courses, and 25 research groups from the U. of Utah, BYU, Utah State and local industry. A rough draft can be copied by anonymous ftp from /usr/spool/ftp/pub/guide.doc from the cs.utah.edu machine. A final draft in plain text and a Macintosh version(better format) will be on the ftp site in about 2 weeks. Sincerely, Jerome B. Soller Ph. D. Student Department of Computer Science University of Utah ------------------------------ Subject: Cognitive Science at Birmingham From: PetersonDM@computer-science.birmingham.ac.uk Date: Thu, 21 Mar 91 15:18:34 +0000 ============================================================================ University of Birmingham Graduate Studies in COGNITIVE SCIENCE ============================================================================ The Cognitive Science Research Centre at the University of Birmingham comprises staff from the Departments/Schools of Psychology, Computer Science, Philosophy and Linguistics, and supports teaching and research in the inter-disciplinary investigation of mind and cognition. The Centre offers both MSc and PhD programmes. MSc in Cognitive Science The MSc programme is a 12 month conversion course, including a 4 month supervised project. The course places a particular stress on the relation between biological and computational architectures. Compulsory courses: AI Programming, Overview of Cognitive Science, Knowledge Representation Inference and Expert Systems, General Linguistics, Human Information Processing, Structures for Data and Knowledge, Philosophical Questions in Cognitive Science, Human-Computer Interaction, Biological and Computational Architectures, The Computer and the Mind, Current Issues in Cognitive Science. Option courses: Artificial and Natural Perceptual Systems, Speech and Natural Language, Parallel Distributed Processing. It is expected that students will have a good degree in psychology, computing, philosophy or linguistics. Funding is available through SERC and HTNT. PhD in Cognitive Science For 1991 there are 3 SERC studentships available for PhD level research into a range of topics including: o computational modelling of emotion o computational modelling of cognition o interface design o computational and psychophysical approaches to vision Computing Facilities Students have access to ample computing facilities, including networks of Apollo, Sun and Sparc workstations in the Schools of Computer Science and Psychology. Contact For further details, contact: Dr. Mike Harris CSRC, School of Psychology, University of Birmingham, PO Box 363, Edgbaston, Birmingham B15 2TT, UK. Phone: (021) 414 4913 Email: HARRIMWG@ibm3090.bham.ac.uk ------------------------------ Subject: POSITIONS IN NEURAL NETWORKS From: Benny Lautrup <LAUTRUP@nbivax.nbi.dk> Date: Thu, 28 Mar 91 11:22:00 +0100 POSITIONS AVAILABLE IN NEURAL NETWORKS Recently, the Danish Research Councils funded the setting up of a Computational Neural Network Centre (CONNECT). There will be some positions as graduate students, postdocs, and more senior visiting scientists available in connection with the centre. Four of the junior (i.e. student and postdoc) positions will be funded directly from the centre grant and have been allotted to the main activity areas as described below. We are required to fill these very quickly to get the centre up and running according to the plans of the program under which it was funded, so the deadline for applying for them is very soon, APRIL 25. If there happen to be exceptionally qualified people in the relevant areas available right now, they should inform us immediately. We are also sending this letter because there may be other positions available in the future. These will generally be externally funded. Normally the procedure would be for us first to identify the good candidate and then to apply to research councils, foundations and/or international programs (e.g. NATO, EC, Nordic Council) for support. This requires some time, so if an applicant is interested in coming here from the fall of 1992, the procedure should be underway in the fall of 1991. The four areas for the present positions are: Biological sequence analysis Development of new theoretical tools and computational methods for analyzing the macromolecular structure and function of biological sequences. The focus will be on applying these tools and methods to specific problems in biology, including pre-mRNA splicing and similarity measures for DNA sequences to be used in constructing phylogenetic trees. The applicant is expected to have a thorough knowledge of experimental molecular biology, coupled with experience in mathematical methods for describing complex biological phenomena. This position will be at the Department of Structural Properties of Materials and the Institute for Physical Chemistry at the Technical University of Denmark. Analog VLSI for neural networks Development of VLSI circuits in analog CMOS for the implementation of neural networks and their learning algorithms. The focus will be on the interaction between network topology and the constraints imposed by VLSI technology. The applicant is expected to have a thorough knowledge of CMOS technology and analog electronics. Experience with the construction of large systems in VLSI, particularly combined analog-digital systems, is especially desirable. This position will be in the Electronics Institute at the Technical University of Denmark. Neural signal processing Theoretical analysis and implementation of new methods for optimizing architectures for neural networks, with applications in adaptive signal processing, as well as ``early vision''. The applicant is expected to have experience in mathematical modelling of complex systems using statistical or statistical mechanical methods. This position will be jointly in the Electronics Institute at the Technical University of Denmark and the Department of Optics and Fluid Dynamics, Risoe National Laboratory. Optical neural networks Theoretical and experimental investigation of optical neural networks. The applicant is expected to have a good knowledge of applied mathematics, statistics, and modern optics, particularly Fourier optics. This position will be in the Department of Optics and Fluid Dynamics, Risoe National Laboratory. In all cases, the applicant is expected to have some background in neural networks and experience in programming in high-level languages. An applicant should send his or her curriculum vitae and publication list to Benny Lautrup Niels Bohr Institute Blegdamsvej 17 DK-2100 Copenhagen Denmark Telephone: (45)3142-1616 Telefax: (45)3142-1016 E-mail: lautrup@nbivax.nbi.dk before April 25. He/she should also have two letters of reference sent separately by people familiar with his/her work by the same date. ------------------------------ Subject: Johns Hopkins' search for applications to aid disabled From: Russ Eberhart <RCE1%APLVM.BITNET@CUNYVM.CUNY.EDU> Date: Thu, 28 Mar 91 11:58:17 -0500 Neuron Digest Announcement JOHNS HOPKINS LAUNCHES NATIONAL SEARCH FOR COMPUTING APPLICATIONS TO ASSIST PERSONS WITH DISABILITIES The Johns Hopkins University is now conducting a nationwide search for Computing Applications to Assist Persons with Disabilities which will run through February 1992. The search is a competition for ideas, systems, devices and computer programs designed to help the more than 25 million Americans with physical or learning disabilities. Systems and devices using neural network technology are obvious candidates. The search is open to all residents of the United States. Amateurs, computer professionals and students are invited to compete for hundreds of prizes and awards including a $10,000 Grand Prize. Entries may address any physical, mental, or learning disability and are due by August 23, 1991. Regional events, competitions and exhibits will be held across the country from now through December 7 of this year, with progress reports and announcements being made through local and national media. Regional winners will compete for the grand prize at the national exhibit and awards ceremony in Washington, D.C. February 1 and 2, 1992. The primary goal for the search is putting ingenuity and technology to work for _people_. To obtain a flier giving details of the competition and how you can participate, write to: Computing to Assist Persons with Disabilities Johns Hopkins National Search P. O. Box 1200 Laurel, MD 20723 or email your request to rce1@aplvm.bitnet. ------------------------------ Subject: Postdoc at U of Edinburgh From: D J Wallace <egnp46@castle.edinburgh.ac.uk> Date: Fri, 29 Mar 91 14:50:51 +0700 POSTDOCTORAL POSITION IN NEURAL NETWORK MODELS AND APPLICATIONS PHYSICS DEPARTMENT, UNIVERSITY OF EDINBURGH Applications are invited for a postdoctoral reasearch position in the Physics Department, University of Edinburgh funded by a Science and Engineering Research Council grant to David Wallace and Alastair Bruce. The position is for two years, from October 1991. The group's interests span theoretical and computational studies of training algorithms, generalisation, dynamical behaviour and optimisation. Theoretical techniques utilise statistical mechanics and dynamical systems. Computational facilities include a range of systems in Edinburgh Parallel Computing Centre, including a 400-node 1.8Gbyte transputer system, a 64-node 1Gbyte Meiko i860 machine and AMT DAPs, as well as workstations and graphics facilities. There are strong links with researchers in other departments, including David Willshaw and Keith Stenning (Cognitive Science), Richard Rohwer (Speech Technology), Alan Murray (Electrical Engineering) and Michael Morgan and Richard Morris (Pharmacology), and we are in two European Community Twinnings. Industrial collaborations have included applications with British Gas, British Petroleum, British Telecom, National Westminster Bank and Shell. Applications supported by a cv and two letters of reference should be sent to D.J. Wallace Physics Department, University of Edinburgh, Kings Buildings, Edinburgh EH9 3JZ, UK Email: ADBruce@uk.ac.ed and DJWallace@uk.ac.ed Tel: 031 650 5250 or 5247 to arrive if possible by 30th April. Further particulars can be obtained from the same address. ------------------------------ Subject: Summer/WInter Fellowships at DEC/Europe From: <pau@yippee.enet.dec.com> Date: Fri, 29 Mar 91 07:16:32 -0800 STUDENT SUMMER (or WINTER) FELLOWSHIPS AT DIGITAL EQUIPMENT ERUOPE's European technical center,Sophia Antipolis,France Digital Equipment Europe is actively pursuing neural processing research and project work worldwide. As part of these activities, the DEC Europe European technical center hosts on a continuing basis student fellows at the MsC or PhD level,for work mostly on: -neural processing in text and image information retrieval -signal understanding for instrumentation and process control -neural processing for banking and financial applications -hybrid systems (neural+expert systems),e.g. for transportation scheduling -embedded NN classifiers in machine vision applications The fellowship durations are to be a minimum of 3 months, with the maximum of 6 months or less, as set by visa or work permit obligations; preference will go to european (but also asian) applications; work language is primarily english. DEC cannot cover travel expenses, but pays a fixed monthly trainee allowance covering housing and food, and dependent on diplomas/work experience .Applications can be sent any time to: Dr L.F.Pau, Technical director, DEC Europe,POBox 129,F 06561 Valbonne, France; it must include: full C.V., photos, copy of last diploma, 2 page statement of experience/courses taken in NN, proof of student registration, and preferably 2 letters of recommendation by faculty.It can be arranged for that the project work reports ,in some cases, can be used in part,to comply with project requirements and grading at the home institution.The working environment requires familiarity with workstations and VMS or UNIX or DOS operating systems. ------------------------------ Subject: AI and NN: industrial applications From: <pau@yippee.enet.dec.com> Date: Fri, 29 Mar 91 07:16:32 -0800 AI and NN: industrial applications In response to a few requests posted on this BB,this is to bring to your attention the following paper,covering extensive industrail projects,and the llearnings made. L.F.Pau,F.S.Johansen, Neural network signal understanding for instrumentation, IEEE Trans. on instrumentation and measurement,Vol 39, no 4,august 1990,558-564 Abstract:This paper reports on the use of neural signal interpretation theory and techniques for the purpose of classifying the shapes of a set of instrumentation signals,in order to calibrate devices,diagnose anomalies,generate tuning/settings,and interpret the measurement results.Neural signal unerstanding research is surveyed,and the selected implementation is described with its performance in terms of correct classification rates and robustness to noise.Formal results on neural net training time and sensitivity to weights are given.A theory for neural control is given using functional link nets and an explanation technique is designed to help neural signal understanding.The results of this are compared to those of a knowledge based signal interpretation system within the context of the same specific instrument and data. ------------------------------ Subject: Applications of ANN in Finance and Banking From: <pau@yippee.enet.dec.com> Date: Fri, 29 Mar 91 07:16:32 -0800 BOOK INCLUDING APPLICATIONS OF NN IN FINANCE AND BANKING The following book has appeared which features chapters on the use of neural networks, as well as inductive learning,on about 10 different financial applications,besides detailing out the most advances knowledge based techniques in those areas: L.F.Pau,C.Gianotti, Economic and financial knowledge based systems, Springer Verlag, NY and Heidelberg, 1990 ------------------------------ Subject: Boolean Models(GSN) From: ecdbcf@ukc.ac.uk Date: Mon, 25 Feb 91 17:07:30 +0000 Dear Connectionists, Most people who read this mail will probably be working with continuous/analogue models. There is, however, a growing interest in Boolean neuron models, and some readers might be interested to know that I have recently successfully completed a Ph.D thesis which deals with a particular kind of Boolean neuron. Some brief details are given below, together with some references to more detailed material. =----------------------------------------------------------------------- Abstract This thesis is concerned with the investigation of Boolean neural networks based on a novel RAM-based Goal-Seeking Neuron(GSN). Boolean neurons are particularly suited to the solution of Boolean or logic problems such as the recognition and associative recall of binarised patterns. One main advantage of Boolean neural networks is the ease with which they can be implemented in hardware. This can result in very fast operation. The GSN has been formulated to ensure this implementation advantage is not lost. The GSN model operates through the interaction of a number of local low level goals and is applicable to practical problems in pattern recognition with only a single pass of the training data(one-shot learning). The thesis explores different architectures for GSNs (feed-forward, feedback and self-organising) together with different learning rules, and investigates a wide range of alternative configurations within these three architectures. Practical results are demonstrated in the context of a character recognition problem. =----------------------------------------------------------------------- Highlights of GSNs, Learning Algorithms, Architectures and Main Contributions The main advantage of RAM-based neural networks in comparison with networks based on sum-of-products functions is the ease with which they can be implemented in hardware. This derives from their essentially logical rather than continuous nature. The GSN model has a natural propensity to solve the main problems associated with other RAM-based neurons. Specific classes of computational activity can be more appropriately realised by using a particular goal seeking function, and different kinds of goal seeking functions can be sought in order to provide a range of suitable behaviour, creating effectively a family of GSNs. The main experimental results have demonstrated the viability of the one-shot learning algorithms: partial pattern association, quasi-self-organisation, and self-organisation. The one-shot learning is only possible because of the the GSN's ability to validate the possibility of learning a given input pattern using a single presentation. The partial pattern association and the quasi-self-organising learning have been applied in feed-forward architectures. These two kinds of learning have given similar performance, though the quasi-self-organising learning gives slightly better results when a small training size is considered. The work reported has established the viability and basic effectiveness of the GSN concept. The GSN proposal provides a new range of computational units, learning algorithms, architectures, and new concepts related to the fundamental processes of computation using Boolean networks. In all of these ideas further modifications, extensions, and applications can be considered in order fully to establish Boolean neural networks as a strong candidate for solving Boolean-type problems. A great deal of additional research can be identified for immediate investigation as follows. One of the most important contributions of this work is the idea of flexible local goals in RAM-based neurons which allows the application of RAM-based neurons and architectures to a wider range of problems. The definition of the goal seeking functions for all the GSN models used in the feed-forward, feedback and self-organising architectures are important because they provide local goals which try to maximise the memory capacity and to improve the recall of correct output patterns. Although the supervised pattern association learning is not the kind of learning most suitable for use with GSN networks, because it demands multi-presentations of the training set and causes a fast saturation of the neurons' contents, the variety of solutions presented to the problem of conflict of learning can help to achieve correct learning with a relatively small number of activations compared to the traditional way of erasing a path without taking care to keep the maximum number of stored patterns. The partial pattern association, quasi-self-organising, and the self-organising learning have managed to break away from the traditional necessity for many thousands of presentations of the training set, and instead have concentrated on providing one-shot learning. This is made possible by the propagation of the undefined value between the neurons in conjunction with the local goal used in the validating state. Due to the partial coverage area and the limited functionality of the pyramids, which can cause an inability to learn particular patterns, it is important to change the desired output patterns in order to be able to learn these classes. The network produces essentially self-desired output patterns which are similar to the desired output patterns, but not necessarily the same. The differences between the desired output patterns and the self-desired output patterns can be observed in the learning phase by looking at the output values of each pyramid and the desired output values. The definition of the self-desired and the learning probability recall rules have provided a way of sensing the changes in the desired output patterns, and of achieving the required pattern classification. The principle of low connectivity and partial coverage area make possible more realistic VLSI implementations in terms of memory requirements and overall connection complexity associated with the traditional problem of fan-in and fan-out for high connectivity neurons. The feedback architecture is able to achieve associative recall and pattern completion, demonstrating that it is possible to have a cascade of feedback networks that incrementally increases the similarity between a prototype and the output patterns. The utilisation of the freeze feedback operation has given a high percentage of correct convergences and fast stabilisation of the output patterns. The analysis of the saturation problem has demonstrated that the traditional way of using uniform connectivity for all the layers impedes the advance of the learning process and many memory addresses remain unused. This is because saturation is not at the same level for each of the layers. Thus, a new approach has been developed to assign a varied connectivity to the architecture which can achieve a better capacity of learning, a lower level of saturation and a smaller residue of unused memory. In terms of architectures and learning, an important result is the design of the GSN self-organising network which incorporates some principles related to the Adaptive Resonance Theory(ART). The self-organising network contains intrinsic mechanisms to prevent the explosion of the number of clusters necessary for self-stabilising a given training pattern set. Several interesting properties are found in the GSN self-organising network such as: attention, discrimination, generalisation, self-stabilisation, and so on. References @conference{key210, author = "D L Bisset And E C D B C Filho And M C Fairhurst", title = "A Comparative study of neural network structures for practical application in a pattern recognition enviroment", publisher= "IEE", booktitle= "Proc. First IEE International Conference on Artificial Neural Networks", address = "London, UK", month = "October", pages = "378-382", year = "1989" } @conference{key214, author = "E C D B C Filho And D L Bisset And M C Fairhurst", title = "A Goal Seeking Neuron For {B}oolean Neural Networks", publisher= "IEEE", booktitle= "Proc. International Neural Networks Conference", address = "Paris, France", month = "July", volume = "2", pages = "894-897", year = "1990" } @article{key279, author = "E C D B C Filho And D L Bisset And M C Fairhurst", title = "Architectures for Goal-Seeking Neurons", journal= "International Journal of Intelligent Systems", publisher= "John Wiley & Sons, Inc", note = "To Appear", year = "1991" } @article{key280, author = "E C D B C Filho And M C Fairhurst And D L Bisset", title = "Adaptive Pattern Recognition Using Goal-Seeking Neurons", journal= "Pattern Recognition Letters", publisher= "North Holland", month = "March" year = "1991" } All the best, Edson ... Filho -- After 10-Mar-91 ----------------------------------------------------------- ! Universidade Federal de Pernambuco ! e-mail: edson@di0001.ufpe.anpe.br ! ! Departamento de Informatica ! Phone: (81) 2713052 ! ! Av. Prof. Luis Freire, S/N ! ! ! Recife --- PE --- Brazil --- 50739 ! ! ------------------------------------------------------------------------------ ------------------------------ End of Neuron Digest [Volume 7 Issue 16] ****************************************