A new Jacobian matrix for optimal learning of single-layer neural networks

This paper investigates the learning of a wide class of single-hidden-layer feedforward neural networks (SLFNs) with two sets of adjustable parameters, i.e., the nonlinear parameters in the hidden nodes and the linear output weights. The main objective is to both speed up the convergence of second-order learning algorithms such as Levenberg-Marquardt (LM), as well as to improve the network performance. This is achieved here by reducing the dimension of the solution space and by introducing a new Jacobian matrix. Unlike conventional supervised learning methods which optimize these two sets of parameters simultaneously, the linear output weights are first converted into dependent parameters, thereby removing the need for their explicit computation. Consequently, the neural network (NN) learning is performed over a solution space of reduced dimension. A new Jacobian matrix is then proposed for use with the popular second-order learning methods in order to achieve a more accurate approximation of the cost function. The efficacy of the proposed method is shown through an analysis of the computational complexity and by presenting simulation results from four different examples.

Engineering source/drain extension regions in nanoscale double gate (DG) SOI MOSFETs: Analytical model and design considerations

In this paper, we propose for the first time, an analytical model for short channel effects in nanoscale source/drain extension region engineered double gate (DG) SOI MOSFETs. The impact of (i) lateral source/drain doping gradient (d), (ii) spacer width (s), (iii) spacer to doping gradient ratio (s/d) and (iv) silicon film thickness (T-si), on short channel effects - threshold voltage (V-th) and subthreshold slope (S), on-current (I-on), off-current (I-on) and I-on/I-off is extensively analysed by using the analytical model and 2D device simulations. The results of the analytical model confirm well with simulated data over the entire range of spacer widths, doping gradients and effective channel lengths. Results show that lateral source/drain doping gradient along with spacer width can not only effectively control short channel effects, thus presenting low off-current, but can also be optimised to achieve high values of on-currents. The present work provides valuable design insights in the performance of nanoscale DG Sol devices with optimal source/drain engineering and serves as a tool to optimise important device and technological parameters for 65 nm technology node and below. (c) 2006 Elsevier Ltd. All rights reserved.

Linear quadratic and tumour control probability modelling in external beam radiotherapy

The standard linear-quadratic (LQ) survival model for external beam radiotherapy is reviewed with particular emphasis on studying how different schedules of radiation treatment planning may be affected by different tumour repopulation kinetics. The LQ model is further examined in the context of tumour control probability (TCP) models. The application of the Zaider and Minerbo non-Poissonian TCP model incorporating the effect of cellular repopulation is reviewed. In particular the recent development of a cell cycle model within the original Zaider and Minerbo TCP formalism is highlighted. Application of this TCP cell-cycle model in clinical treatment plans is explored and analysed.