An ordering algorithm for pattern presentation in fuzzy ARTMAP thattends to improve generalization performance

We introduce a procedure, based on the max-min clustering method, that identifies a fixed order of training pattern presentation for fuzzy adaptive resonance theory mapping (ARTMAP). This procedure is referred to as the ordering algorithm, and the combination of this procedure with fuzzy ARTMAP is referred to as ordered fuzzy ARTMAP. Experimental results demonstrate that ordered fuzzy ARTMAP exhibits a generalization performance that is better than the average generalization performance of fuzzy ARTMAP, and in certain cases as good as, or better than the best fuzzy ARTMAP generalization performance. We also calculate the number of operations required by the ordering algorithm and compare it to the number of operations required by the training phase of fuzzy ARTMAP. We show that, under mild assumptions, the number of operations required by the ordering algorithm is a fraction of the number of operations required by fuzzy ARTMAP.     

A general framework for concurrent simulation on neural networkmodels

The analysis of complex neural network models via analytical techniques is often quite difficult due to the large numbers of components involved and the nonlinearities associated with these components. The authors present a framework for simulating neural networks as discrete event nonlinear dynamical systems. This includes neural network models whose components are described by continuous-time differential equations or by discrete-time difference equations. Specifically, the authors consider the design and construction of a concurrent object-oriented discrete event simulation environment for neural networks. The use of an object-oriented language provides the data abstraction facilities necessary to support modification and extension of the simulation system at a high level of abstraction. Furthermore, the ability to specify concurrent processing supports execution on parallel architectures. The use of this system is demonstrated by simulating a specific neural network model on a general-purpose parallel computer     

Solid Lipid Curcumin Particles Protect Medium Spiny Neuronal Morphology,and Reduce Learning and Memory Deficits in the YAC128 Mouse Model of Huntington’s Disease

Huntington’s disease (HD) is a genetic neurodegenerative disorder characterized by motor, cognitive, and psychiatric symptoms, accompanied by massive neuronal degeneration in the striatum. In this study, we utilized solid lipid curcumin particles (SLCPs) and solid lipid particles (SLPs) to test their efficacy in reducing deficits in YAC128 HD mice. Eleven-month-old YAC128 male and female mice were treated orally with SLCPs (100 mg/kg) or equivalent volumes of SLPs or vehicle (phosphate-buffered saline) every other day for eight weeks. Learning and memory performance was assessed using an active-avoidance task on week eight. The mice were euthanized, and their brains were processed using Golgi-Cox staining to study the morphology of medium spiny neurons (MSNs) and Western blots to quantify amounts of DARPP-32, brain-derived neurotrophic factor (BDNF), TrkB, synaptophysin, and PSD-95. We found that both SLCPs and SLPs improved learning and memory in HD mice, as measured by the active avoidance task. We also found that SLCP and SLP treatments preserved MSNs arborization and spinal density and modulated synaptic proteins. Our study shows that SLCPs, as well as the lipid particles, can have therapeutic effects in old YAC128 HD mice in terms of recovering from HD brain pathology and cognitive deficits.