Learning real-world stimuli in a neural network with spike-driven synaptic dynamics

We present a model of spike-driven synaptic plasticity inspired by experimental observations and motivated by the desire to build an electronic hardware device that can learn to classify complex stimuli in a semisupervised fashion. During training, patterns of activity are sequentially imposed on the input neurons, and an additional instructor signal drives the output neurons toward the desired activity. The network is made of integrate-and-fire neurons with constant leak and a floor. The synapses are bistable, and they are modified by the arrival of presynaptic spikes. The sign of the change is determined by both the depolarization and the state of a variable that integrates the postsynaptic action potentials. Following the training phase, the instructor signal is removed, and the output neurons are driven purely by the activity of the input neurons weighted by the plastic synapses. In the absence of stimulation, the synapses preserve their internal state indefinitely. Memories are also very robust to the disruptive action of spontaneous activity. A network of 2000 input neurons is shown to be able to classify correctly a large number (thousands) of highly overlapping patterns (300 classes of preprocessed Latex characters, 30 patterns per class, and a subset of the NIST characters data set) and to generalize with performances that are better than or comparable to those of artificial neural networks. Finally we show that the synaptic dynamics is compatible with many of the experimental observations on the induction of long-term modifications (spike-timing-dependent plasticity and its dependence on both the postsynaptic depolarization and the frequency of pre- and postsynaptic neurons).

Neural network based glucose - insulin metabolism models for children with Type 1 diabetes

In this paper two models for the simulation of glucose-insulin metabolism of children with Type 1 diabetes are presented. The models are based on the combined use of Compartmental Models (CMs) and artificial Neural Networks (NNs). Data from children with Type 1 diabetes, stored in a database, have been used as input to the models. The data are taken from four children with Type 1 diabetes and contain information about glucose levels taken from continuous glucose monitoring system, insulin intake and food intake, along with corresponding time. The influences of taken insulin on plasma insulin concentration, as well as the effect of food intake on glucose input into the blood from the gut, are estimated from the CMs. The outputs of CMs, along with previous glucose measurements, are fed to a NN, which provides short-term prediction of glucose values. For comparative reasons two different NN architectures have been tested: a Feed-Forward NN (FFNN) trained with the back-propagation algorithm with adaptive learning rate and momentum, and a Recurrent NN (RNN), trained with the Real Time Recurrent Learning (RTRL) algorithm. The results indicate that the best prediction performance can be achieved by the use of RNN.

A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier

In this paper, a computer-aided diagnostic (CAD) system for the classification of hepatic lesions from computed tomography (CT) images is presented. Regions of interest (ROIs) taken from nonenhanced CT images of normal liver, hepatic cysts, hemangiomas, and hepatocellular carcinomas have been used as input to the system. The proposed system consists of two modules: the feature extraction and the classification modules. The feature extraction module calculates the average gray level and 48 texture characteristics, which are derived from the spatial gray-level co-occurrence matrices, obtained from the ROIs. The classifier module consists of three sequentially placed feed-forward neural networks (NNs). The first NN classifies into normal or pathological liver regions. The pathological liver regions are characterized by the second NN as cyst or "other disease." The third NN classifies "other disease" into hemangioma or hepatocellular carcinoma. Three feature selection techniques have been applied to each individual NN: the sequential forward selection, the sequential floating forward selection, and a genetic algorithm for feature selection. The comparative study of the above dimensionality reduction methods shows that genetic algorithms result in lower dimension feature vectors and improved classification performance.

Grey matter volumetric changes related to recovery from hand paresis after cortical sensorimotor stroke

Preclinical studies using animal models have shown that grey matter plasticity in both perilesional and distant neural networks contributes to behavioural recovery of sensorimotor functions after ischaemic cortical stroke. Whether such morphological changes can be detected after human cortical stroke is not yet known, but this would be essential to better understand post-stroke brain architecture and its impact on recovery. Using serial behavioural and high-resolution magnetic resonance imaging (MRI) measurements, we tracked recovery of dexterous hand function in 28 patients with ischaemic stroke involving the primary sensorimotor cortices. We were able to classify three recovery subgroups (fast, slow, and poor) using response feature analysis of individual recovery curves. To detect areas with significant longitudinal grey matter volume (GMV) change, we performed tensor-based morphometry of MRI data acquired in the subacute phase, i.e. after the stage compromised by acute oedema and inflammation. We found significant GMV expansion in the perilesional premotor cortex, ipsilesional mediodorsal thalamus, and caudate nucleus, and GMV contraction in the contralesional cerebellum. According to an interaction model, patients with fast recovery had more perilesional than subcortical expansion, whereas the contrary was true for patients with impaired recovery. Also, there were significant voxel-wise correlations between motor performance and ipsilesional GMV contraction in the posterior parietal lobes and expansion in dorsolateral prefrontal cortex. In sum, perilesional GMV expansion is associated with successful recovery after cortical stroke, possibly reflecting the restructuring of local cortical networks. Distant changes within the prefrontal-striato-thalamic network are related to impaired recovery, probably indicating higher demands on cognitive control of motor behaviour.