In this paper, two popular types of neural network models (radial base function (RBF) and multi-layered feed-forward (MLF) networks) trained by the generalized delta rule, are tested on their robustness to random errors in input space. A method is proposed to estimate the sensitivity of network outputs to the amplitude of random errors in the input space, sampled from known normal distributions...

Coupling between pyramidal tract (PT) neurones and ipsilateral hindlimb motoneurones was investigated by recording from commissural interneurones interposed between them. Near maximal stimulation of either the left or right PT induced short latency EPSPs in more than 80% of 20 commissural interneurones that were monosynaptically excited by reticulospinal tract fibres in the medial longitudinal ...

Effects of stimulation of ipsilateral pyramidal tract (PT) fibres were analysed in interneurones in midlumbar segments of the cat spinal cord in search of interneurones mediating disynaptic actions of uncrossed PT fibres on hindlimb motoneurones. The sample included 44 intermediate zone and ventral horn interneurones, most with monosynaptic input from group I and/or group II muscle afferents an...

An Adaptive Resonance Theory Based Artificial Neural Network (ART-2a) has been compared with Multilayer Feedforward Backpropagation of Error Neural Networks (MLF-BP) and with the SIMCA classifier. All three classifiers were applied to achieve rapid sorting of post-consumer plastics by remote near-infrared (NIR) spectroscopy. A new semiconductor diode array detector based on InGaAs technology ha...

As a consequence of the alcoholic fermentation carried out by yeasts in wine, several compounds can be delivered to medium, promoting or inhibiting malolactic (MLF) and lactic acid bacteria, mainly Oenococcus oeni. Succinic is one these an example interaction between yeasts, including non-Saccharomyces species, O. However, influence succinic on MLF has been researched very little as yet. In thi...

Many sensor-based control systems are dynamically changing, and thus require a flexible scheduler. The rate monotonic (RM) real-time scheduling algorithm does not support such dynamic systems very well. On the other hand, with earliest-deadline-first (EDF) and minimum-laxity-first (MLF) dynamic scheduling algorithms, a transient overload in the system may cause a critical task to fail, which is...

(Abstract) Compiling Bayesian networks (BNs) is one of the hot topics in the area of probabilistic modeling and processing. In this paper, we propose a new method of compiling BNs into multi-linear functions (MLFs) based on Zero-suppressed BDDs (ZBDDs), which are the graph-based representation of combinatorial item sets. Our method is different from the original approach of Darwiche et. al whic...

Bidding competition is one of the main transaction approaches in a deregulated electricity market. Locational marginal prices (LMPs) resulting from bidding competition and system operation conditions indicate electricity values at a node or in an area. The LMP reveals important information for market participants in developing their bidding strategies. Moreover, LMP is also a vital indicator fo...

MLF is a type system that seamlessly merges ML-style implicit but second-class polymorphism with System-F explicit first-class polymorphism. We present xMLF, a Church-style version of MLF with full type information that can easily be maintained during reduction. All parameters of functions are explicitly typed and both type abstraction and type instantiation are explicit. However, type instanti...

This research note presents reactions to Jake, Myers-Scotton and Gross’s (2005) response to MacSwan (2005), the latter offered as a response to Jake, Myers-Scotton and Gross (2002) and as a general critique of the MLF model of Myers-Scotton and colleagues. The note responds to the authors’ analysis of various linguistic examples and to their continued assertion that the MLF model (and “matrix l...