If N hin then such a perceptron must have all units of the first hidden layer fully connected to inputs. This implies the maximal capacities (in the sense of Cover) of 2n input patterns per hidden unit and 2 input patterns per synaptic weight of such networks (both capacities are achieved by networks with single hidden layer and are the same as for a single neuron). Comparing these results with recent estimates of VC-dimension we find that in contrast to the single neuron case, for sufficiently large nand hl, the VC-dimension exceeds Cover's capacity. 1 Introduction In the course of theoretical justification of many of the claims made about neural networks regarding their ability to learn a set of patterns and their ability to generalise, various concepts of maximal storage capacity were developed. In particular Cover's capacity [4] and VC-dimension [12] are two expressions of this notion and are of special interest here. We should stress that both capacities are not easy to compute and are presen tly known in a few particular cases of feedforward networks only.

The first class of network adaptation algorithms start out with a redundant architecture and proceed by pruning away seemingly unimportant weights (Sietsma and Dow, 1988; Le Cun et aI, 1990). A second class of algorithms starts off with a sparse architecture and grows the network to the complexity required by the problem. Several algorithms have been proposed for growing feedforward networks. The upstart algorithm of Frean (1990) and the cascade-correlation algorithm of Fahlman (1990) are examples of this approach.

University of Rochester) and ICSIM (lCSI Berkeley) allow the definition of unit types and complex connectivity patterns. On a very high level of abstraction, simulators like tleam (UCSD) allow the easy realization of predefined network architectures (feedforward networks) and leaming algorithms such as backpropagation. Ben Gomes, International Computer Science Institute (Berkeley) introduced the Connectionist Supercomputer 1. The CNSl is a multiprocessor system designed for moderate precision fixed point operations used extensively in connectionist network calculations. Custom VLSI digital processors employ an on-chip vector coprocessor unit tailored for neural network calculations and controlled by RISC scalar CPU.

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.

This study explores the extent to which a network that learns the temporal relationships within and between the component features of Western tonal music can account for music theoretic and psychological phenomena such as the tonal hierarchy and rhythmic expectancies. Predicted and generated sequences were recorded as the representation of a 153-note waltz melody was learnt by a predictive, recurrent network. The network learned transitions and relations between and within pitch and timing components: accent and duration values interacted in the development of rhythmic and metric structures and, with training, the network developed chordal expectancies in response to the activation of individual tones. Analysis of the hidden unit representation revealed that musical sequences are represented as transitions between states in hidden unit space.

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

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 acute when 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.

If N hin then such a perceptron must have all units of the first hidden layer fully connected to inputs. This implies the maximal capacities (in the sense of Cover) of 2n input patterns per hidden unit and 2 input patterns per synaptic weight of such networks (both capacities are achieved by networks with single hidden layer and are the same as for a single neuron). Comparing these results with recent estimates of VC-dimension we find that in contrast to the single neuron case, for sufficiently large nand hl, the VC-dimension exceeds Cover's capacity. 1 Introduction In the course of theoretical justification of many of the claims made about neural networks regarding their ability to learn a set of patterns and their ability to generalise, various concepts of maximal storage capacity were developed. In particular Cover's capacity [4] and VC-dimension [12] are two expressions of this notion and are of special interest here. We should stress that both capacities are not easy to compute and are presen tly known in a few particular cases of feedforward networks only.

The first class of network adaptation algorithms start out with a redundant architecture and proceed by pruning away seemingly unimportant weights (Sietsma and Dow, 1988; Le Cun et aI, 1990). A second class of algorithms starts off with a sparse architecture and grows the network to the complexity required by the problem. Several algorithms have been proposed for growing feedforward networks. The upstart algorithm of Frean (1990) and the cascade-correlation algorithm of Fahlman (1990) are examples of this approach.

University of Rochester) and ICSIM (lCSI Berkeley) allow the definition of unit types and complex connectivity patterns. On a very high level of abstraction, simulators like tleam (UCSD) allow the easy realization of predefined network architectures (feedforwardnetworks) and leaming algorithms such as backpropagation. Ben Gomes, International Computer Science Institute (Berkeley) introduced the Connectionist Supercomputer 1. The CNSl is a multiprocessor system designed for moderate precision fixed point operations used extensively in connectionist network calculations. Custom VLSI digital processors employ an on-chip vector coprocessor unit tailored for neural network calculations and controlled by RISC scalar CPU. One processor and associated commercial DRAM comprise a node, which is connected in a mesh topology with other nodes to establish a MIMD array. One edge of the communications meshis reserved for attaching various 110 devices, which connect via a custom network adaptor chip. The CNSl operates as a compute server and one 110 port is used for connecting to a host workstation. Users with mainstream connectionist applications can use CNSim, an object-oriented, graphical high-level interface to the CNSl environment.