This paper describes a low power analogue VLSI neural network called Wattle. Wattle is a 10:6:4 three layer perceptron with multiplying DACsynapses and on chip switched capacitor neurons fabricated in 1.2um CMOS.

Padhraic Smyth Jet Propulsion Laboratory 238-420 California Institute of Technology 4800 Oak Grove Drive Pasadena, CA 91109 Abstract This paper describes probabilistic methods for novelty detection when using pattern recognition methods for fault monitoring of dynamic systems. The problem of novelty detection is particularly acutewhen prior knowledge and training data only allow one to construct an incomplete classification model. Allowance must be made in model design so that the classifier will be robust to data generated by classes not included in the training phase. For diagnosis applications one practical approach is to construct both an input density model and a discriminative class model. Using Bayes' rule and prior estimates of the relative likelihood of data of known and unknown origin the resulting classification equations are straightforward.

In this paper, we will consider the problem of classifying electroencephalogram (EEG)signals of normal subjects, and subjects suffering from psychiatric disorder, e.g., obsessive compulsive disorder, schizophrenia, using a class of artificial neural networks, viz., multi-layer perceptron. It is shown that the multilayer perceptron is capable of classifying unseen test EEG signals to a high degree of accuracy.

However, extended object-oriented oday, object-oriented programming important and powerful programming Italy, Sweden, the United languages and systems have paradigm, especially for Kingdom, and the United States were been developed that are adequate to the development of complex systems, invited to the workshop. This article handle AI applications. AI, raised and the major points made programming, a case of objectoriented however, is looking for knowledge during the presentations of the eight programming that has a representation and programming papers in the workshop's four sessions. AI, does not satisfy distributed AI applications and uses constructs (for The workshop started with an requirements because it lacks representation, example, frames) and notions (for introduction by Ibrahim in which he communication, and organization. Ibrahim posed a to the object-based concurrent The one-day workshop entitled number of questions related to the programming paradigm to close the Objects and AI, held in Sydney, Australia, theme of the workshop and asked gap with distributed AI, such as the on 25 August 1991 in conjunction the participants to address some of introduction of more powerful object with the 1991 International these questions during their talks and representations, a social theory of Joint Conference on Artificial Intelligence, discussion.

The feed-forward networks with fixed hidden units (FllU-networks) are compared against the category of remaining feed-forward networks with variable hidden units (VHU-networks).

IR is typically a sigmoidal function such as (1.2) but other choices than (1.2) are possible and of interest.

The algorithm presented performs gradient descent on the weight space of an Artificial Neural Network (ANN), using a finite difference to approximate the gradient The method is novel in that it achieves a computational complexity similar to that of Node Perturbation, O(N3), but does not require access to the activity of hidden or internal neurons. This is possible due to a stochastic relation between perturbations at the weights and the neurons of an ANN. The algorithm is also similar to Weight Perturbation in that it is optimal in terms of hardware requirements when used for the training ofVLSI implementations of ANN's.

Holographic Recurrent Networks (HRNs) are recurrent networks which incorporate associative memory techniques for storing sequential structure. HRNs can be easily and quickly trained using gradient descent techniques to generate sequences of discrete outputs and trajectories through continuous spaee. The performance of HRNs is found to be superior to that of ordinary recurrent networks on these sequence generation tasks.

Hidden units in multi-layer networks form a representation space in which each region can be identified with a class of equivalent outputs (Elman, 1989) or a logical state in a finite state machine (Cleeremans, Servan-Schreiber & McClelland, 1989; Giles, Sun, Chen, Lee, & Chen, 1990). We extend the analysis of the spatial structure of hidden unit space to a combinatorial task, based on binding features together in a visual scene. The logical structure requires a combinatorial number of states to represent all valid scenes. On analysing our networks, we find that the high dimensionality of hidden unit space is exploited by using the intersection of neighboring regions to represent conjunctions of features. These results show how combinatorial structure can be based on the spatial nature of networks, and not just on their emulation of logical structure.

The feed-forward networks with fixed hidden units (FllU-networks) are compared against the category of remaining feed-forward networks with variable hidden units (VHU-networks).