Automatic differentiation of multichannel EEG signals

Intention of movement of left or right index finger, or right foot is recognized in electroencephalograms (EEGs) from three subjects. We present a multichannel classification method that uses a "committee" of artificial neural networks to do this. The classification method automatically finds spatial regions on the skull relevant for the classification task. Depending on subject, correct recognition of intended movement was achieved in 75%-98% of trials not seen previously by the committee, on the basis of single EEGs of one-second duration. Frequency filtering did not improve recognition. Classification was optimal during the actual movement, but a first peak in the classification success rate was observed in all subjects already when they had been cued which movement later to perform.

Comparison between human and artificial neural network detection of Laplacian-derived electroencephalographic activity related to unilateral voluntary movements

A back-propagation artificial neural network (ANN) was tested to verify its capacity to select different classes of single trials (STs) based on the spatial information content of electroencephalographic activity related to voluntary unilateral finger movements. The rationale was that ipsilateral and contralateral primary sensorimotor cortex can be involved in a nonstationary way in the control of unilateral voluntary movements. The movement-related potentials were surface Laplacian-transformed (SL) to reduce head volume conductor effects and to model the response of the primary sensorimotor cortex. The ANN sampled the SL from four or two central channels overlying the primary motor area of both sides in the period of 80 ms preceding the electromyographic response onset in the active muscle. The performance of the ANN was evaluated statistically by calculating the percentage value of agreement between the STs classified by the ANN and those of two investigators (used as a reference). The results showed that both investigator and ANN were capable of selecting STs with the SL maximum in the central area contralateral to the movement (contralateral STs, about 25%), STs with considerable SL values also in the ipsilateral central area (bilateral STs, about 50%), and STs with neither the contralateral nor bilateral pattern ("spatially incoherent" single trials; about 25%). The maximum agreement (64-84%) between the ANN and the investigator was obtained when the ANN used four spatial inputs (P < 0.0000001). Importantly, the common means of all single trials showed a weak or absent ipsilateral response. These results may suggest that a back-propagation ANN could select EEG single trials showing stationary and nonstationary responses of the primary sensorimotor cortex, based on the same spatial criteria as the experimenter.

Partially pre-calculated weights for the backpropagation learning regime and high accuracy function mapping using continuous input RAM-based sigma-pi nets

In this article we present a methodology that partially pre-calculates the weight updates of the backpropagation learning regime and obtains high accuracy function mapping. The paper shows how to implement neural units in a digital formulation which enables the weights to be quantised to 8-bits and the activations to 9-bits. A novel methodology is introduced to enable the accuracy of sigma-pi units to be increased by expanding their internal state space. We, also, introduce a novel means of implementing bit-streams in ring memories instead of utilising shift registers. The investigation utilises digital "Higher Order" sigma-pi nodes and studies continuous input RAM-based sigma-pi units. The units are trained with the backpropagation learning regime to learn functions to a high accuracy. The neural model is the sigma-pi units which can be implemented in digital microelectronic technology. The ability to perform tasks that require the input of real-valued information, is one of the central requirements of any cognitive system that utilises artificial neural network methodologies. In this article we present recent research which investigates a technique that can be used for mapping accurate real-valued functions to RAM-nets. One of our goals was to achieve accuracies of better than 1% for target output functions in the range Y epsilon [0,1], this is equivalent to an average Mean Square Error (MSE) over all training vectors of 0.0001 or an error modulus of 0.01. We present a development of the sigma-pi node which enables the provision of high accuracy outputs. The sigma-pi neural model was initially developed by Gurney (Learning in nets of structured hypercubes. PhD Thesis, Department of Electrical Engineering, Brunel University, Middlessex, UK, 1989; available as Technical Memo CN/R/144). Gurney's neuron models, the Time Integration Node (TIN), utilises an activation that was derived from a bit-stream. In this article we present a new methodology for storing sigma-pi node's activations as single values which are averages. In the course of the article we state what we define as a real number; how we represent real numbers and input of continuous values in our neural system. We show how to utilise the bounded quantised site-values (weights) of sigma-pi nodes to make training of these neurocomputing systems simple, using pre-calculated look-up tables to train the nets. In order to meet our accuracy goal, we introduce a means of increasing the bandwidth capability of sigma-pi units by expanding their internal state-space. In our implementation we utilise bit-streams when we calculate the real-valued outputs of the net. To simplify the hardware implementation of bit-streams we present a method of mapping them to RAM-based hardware using 'ring memories'. Finally, we study the sigma-pi units' ability to generalise once they are trained to map real-valued, high accuracy, continuous functions. We use sigma-pi units as they have been shown to have shorter training times than their analogue counterparts and can also overcome some of the drawbacks of semi-linear units (Gurney, 1992. Neural Networks, 5, 289-303).

A reinforcement learning approach to online clustering

A general technique is proposed for embedding online clustering algorithms based on competitive learning in a reinforcement learning framework. The basic idea is that the clustering system can be viewed as a reinforcement learning system that learns through reinforcements to follow the clustering strategy we wish to implement. In this sense, the reinforcement guided competitive learning (RGCL) algorithm is proposed that constitutes a reinforcement-based adaptation of learning vector quantization (LVQ) with enhanced clustering capabilities. In addition, we suggest extensions of RGCL and LVQ that are characterized by the property of sustained exploration and significantly improve the performance of those algorithms, as indicated by experimental tests on well-known data sets.

The Theoretical and Experimental Status of the n-tuple Classifier

A number of theoretical approaches related to the n-tuple classification system are reviewed including Kanerva's SDM, the n-tuple regression network, the Hamming distance framework and likelihood estimation. The limitations of these methods are pointed out and resemblances that exist between them are underlined. Large-scale experiments carried out on StatLog project datasets confirm the n-tuple method as a viable competitor to more popular methods due to its speed, simplicity and accuracy on the majority of a wide variety of classification problems. A further investigation into the failure of the method on certain datasets shows its inner workings and reveals two main problems: difficulties with highly skewed class priors and more importantly, a mismatch between the scales involved in generalization, the amount of training data available, and the volume of the region in which data is likely to exist. This highlights areas where improvements in the method are needed and further theoretical progress would be helpful.

The evolution of a university research department facilitated by a groupware system ‐ Part 2

Discusses how, in Part 1 the research group was at a “pioneering crisis” stage with considerable role and task ambiguity. An organizational development process was initiated aiming for greater systemization: a matrix structure was introduced and a groupware tool, the plan‐document (PD1), was implemented, as part of the group’s strategy to develop into a learning organization. States that the plan‐document was designed to enable information sharing and co‐ordination throughout the group, ranging over the short‐ and long‐terms. Usage was, however, low and PD1 was not widely adopted, although usage varied according to timescales and the personal relevance of objectives. A second plan‐document (PD2) was designed, aimed at being more “personal” and accessible, attuned to the new matrix structure and including reporting as well as planning functions. Looks at the introduction of PD2 and evaluates its contribution to the transition of the research group into both a systematized and a learning organization. Posits that groupware can go some way towards helping organizations meet the challenges of an uncertain environment through supporting open access between groups and individuals and fostering the group cohesiveness and interdependence.