We present a framework for programming tbe bidden unit representations of simple recurrent networks based on the use of hint units (additional targets at the output layer). We present two ways of analysing a network trained within this framework: Input patterns act as operators on the information encoded by the context units; symmetrically, patterns of activation over tbe context units act as curried functions of the input sequences. Simulations demonstrate that a network can learn to represent three different functions simultaneously and canonical discriminant analysis is used to investigate bow operators and curried functions are represented in the space of bidden unit activations.

Box 1600 Salisbury Adelaide SA 5108 Australia T.Downs Intelligent Machines Laboratory Dept of Electrical Engineering University of Queensland Brisbane Q 4072 Australia Abstract This paper is concerned with the problem of learning in networks where some or all of the functions involved are not smooth. Examples of such networks are those whose neural transfer functions are piecewise-linear and those whose error function is defined in terms of the 100 norm. Up to now, networks whose neural transfer functions are piecewise-linear have received very little consideration in the literature, but the possibility of using an error function defined in terms of the 100 norm has received some attention. In this paper we draw upon some recent results from the field of nonsmooth optimization (NSO) to present an algorithm for the nonsmooth case. Our motivation forthis work arose out of the fact that we have been able to show that, in backpropagation, an error function based upon the 100 norm overcomes the difficulties which can occur when using the 12 norm. 1 INTRODUCTION This paper is concerned with the problem of learning in networks where some or all of the functions involved are not smooth.

Connections between spline approximation, approximation with rational functions, and feedforward neural networks are studied. The potential improvement in the degree of approximation in going from single to two hidden layer networks is examined. Some results of Birman and Solomjak regarding the degree of approximation achievable when knot positions are chosen on the basis of the probability distribution of examples rather than the function values are extended.

In this paper, a tree based neural network viz. MARS (Friedman, 1991) for the modelling of the yield strength of a steel rolling plate mill is described. The inputs to the time series model are temperature, strain, strain rate, and interpass time and the output is the corresponding yield stress. It is found that the MARSbased model reveals which variable's functional dependence is nonlinear, and significant. The results are compared with those obta.ined

Thesedevices are implanted and perform three types of actions: l.monitor the heart 2.to pace the heart 3.to apply high energy/high voltage electric shock 1bey sense the electrical activity of the heart through leads attached to the heart tissue. Two types of sensing are commooly used: Single Chamber: Lead attached to the Right Ventricular Apex (RVA) Dual Chamber: An additional lead is attached to the High Right Atrium (HRA). The actions performed by defibrillators are based on the outcome of a classification procedure based on the heart rhythms of different heart diseases (abnormal rhythms or "arrhythmias").

We present a framework for programming tbe bidden unit representations of simple recurrent networks based on the use of hint units (additional targets at the output layer). We present two ways of analysing a network trained within this framework: Input patterns act as operators on the information encoded by the context units; symmetrically, patterns of activation over tbe context units act as curried functions of the input sequences. Simulations demonstrate that a network can learn to represent three different functions simultaneously and canonical discriminant analysis is used to investigate bow operators and curried functions are represented in the space of bidden unit activations.

The Association for the Advancement of Artificial Intelligence held its 1992 Spring Symposium Series on March 25-27 at Stanford University, Stanford, California. This article contains a summary of the symposia that were conducted: Artificial Intelligence in Medicine, Cognitive Aspects of Knowledge Acquisition, Computational Considerations in Supporting Incremental Modification and Reuse, Knowledge Assimilation, Practical Approaches to Scheduling and Planning, Producing Cooperative Explanations, Propositional Knowledge Representation, Selective Perception, and Reasoning with Diagrammatic Representations.

The International Workshop on Processing Declarative Knowledge was held in Kaiserslautern, Germany, from 1 to 3 July 1991. The workshop was intended as a forum for the presentation of new approaches to processing declarative knowledge, the discussion of procedural versus alternative paradigms, and the issues concerned with efficient processing of realistic knowledge bases. Demonstrations of implemented systems were also announced.

The workshop "Advances in Interfacing Production Systems with the Real World" was designed to bring together researchers from around the world to focus on the problem of integrating production systems into industrial environments. It was held on 25 August 1991 in Sydney, Australia, in conjunction with the Twelfth International Joint Conference on Artificial Intelligence (IJCAI-91). Nine papers were accepted for the proceedings, and six of them were discussed at the workshop.

The title of this paper, "On Seeing Robots", leaves substantial scope for playful exploration. The simple ambiguity is, of course, between describing robots that see their worlds and systems that see robots. These categories are not exclusive: I also combine them and discuss robots that see robots and even robots that see themselves. Furthermore, the title is designed to echo, and pay homage to, a classic vision paper entitled "On Seeing Things" by Max Clowes [1] as I have done once before [2]. But the context, the arguments and the conclusions are new; the comparison is used explicitly here to show the difference between the classical approach and an emerging situated approach to robotic perception. The most important reading of the title is that the paper is about how we see robots; it is about the computational paradigms, the assumptions, the architectures and the tools we use to design and build robots.