Verification and FPGA circuits of a block-2 fast path-based predictor

This paper formally derives a new path-based neural branch prediction algorithm (FPP) into blocks of size two for a lower hardware solution while maintaining similar input-output characteristic to the algorithm. The blocked solution, here referred to as B2P algorithm, is obtained using graph theory and retiming methods. Verification approaches were exercised to show that prediction performances obtained from the FPP and B2P algorithms differ within one mis-prediction per thousand instructions using a known framework for branch prediction evaluation. For a chosen FPGA device, circuits generated from the B2P algorithm showed average area savings of over 25% against circuits for the FPP algorithm with similar time performances thus making the proposed blocked predictor superior from a practical viewpoint.

FPGA organization for the fast path-based neural branch predictor

This paper develops cycle-level FPGA circuits of an organization for a fast path-based neural branch predictor Our results suggest that practical sizes of prediction tables are limited to around 32 KB to 64 KB in current FPGA technology due mainly to FPGA area of logic resources to maintain the tables. However the predictor scales well in terms of prediction speed. Table sizes alone should not be used as the only metric for hardware budget when comparing neural-based predictor to predictors of totally different organizations. This paper also gives early evidence to shift the attention on to the recovery from mis-prediction latency rather than on prediction latency as the most critical factor impacting accuracy of predictions for this class of branch predictors.

Clustering quality and topology preservation in fast learning SOMs

The Self-Organizing Map (SOM) is a popular unsupervised neural network able to provide effective clustering and data visualization for data represented in multidimensional input spaces. In this paper, we describe Fast Learning SOM (FLSOM) which adopts a learning algorithm that improves the performance of the standard SOM with respect to the convergence time in the training phase. We show that FLSOM also improves the quality of the map by providing better clustering quality and topology preservation of multidimensional input data. Several tests have been carried out on different multidimensional datasets, which demonstrate better performances of the algorithm in comparison with the original SOM.

A fast identification algorithm for Box-Cox transformation based radial basis function neural network

In this letter, a Box-Cox transformation-based radial basis function (RBF) neural network is introduced using the RBF neural network to represent the transformed system output. Initially a fixed and moderate sized RBF model base is derived based on a rank revealing orthogonal matrix triangularization (QR decomposition). Then a new fast identification algorithm is introduced using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator. The main contribution of this letter is to explore the special structure of the proposed RBF neural network for computational efficiency by utilizing the inverse of matrix block decomposition lemma. Finally, the Box-Cox transformation-based RBF neural network, with good generalization and sparsity, is identified based on the derived optimal Box-Cox transformation and a D-optimality-based orthogonal forward regression algorithm. The proposed algorithm and its efficacy are demonstrated with an illustrative example in comparison with support vector machine regression.

Fast kernel classifier construction using orthogonal forward selection to minimise leave-one-out misclassification rate

We propose a simple yet computationally efficient construction algorithm for two-class kernel classifiers. In order to optimise classifier's generalisation capability, an orthogonal forward selection procedure is used to select kernels one by one by minimising the leave-one-out (LOO) misclassification rate directly. It is shown that the computation of the LOO misclassification rate is very efficient owing to orthogonalisation. Examples are used to demonstrate that the proposed algorithm is a viable alternative to construct sparse two-class kernel classifiers in terms of performance and computational efficiency.

A fast linear-in-the-parameters classifier construction algorithm using orthogonal forward selection to minimize leave-one-out misclassification rate

We propose a simple and computationally efficient construction algorithm for two class linear-in-the-parameters classifiers. In order to optimize model generalization, a forward orthogonal selection (OFS) procedure is used for minimizing the leave-one-out (LOO) misclassification rate directly. An analytic formula and a set of forward recursive updating formula of the LOO misclassification rate are developed and applied in the proposed algorithm. Numerical examples are used to demonstrate that the proposed algorithm is an excellent alternative approach to construct sparse two class classifiers in terms of performance and computational efficiency.

Classification-based probabilistic modeling of texture transition for fast line search tracking and delineation

We introduce a classification-based approach to finding occluding texture boundaries. The classifier is composed of a set of weak learners, which operate on image intensity discriminative features that are defined on small patches and are fast to compute. A database that is designed to simulate digitized occluding contours of textured objects in natural images is used to train the weak learners. The trained classifier score is then used to obtain a probabilistic model for the presence of texture transitions, which can readily be used for line search texture boundary detection in the direction normal to an initial boundary estimate. This method is fast and therefore suitable for real-time and interactive applications. It works as a robust estimator, which requires a ribbon-like search region and can handle complex texture structures without requiring a large number of observations. We demonstrate results both in the context of interactive 2D delineation and of fast 3D tracking and compare its performance with other existing methods for line search boundary detection.

Fast and accurate SCFT calculations for periodic block-copolymer morphologies using the spectral method with Anderson mixing

We study the numerical efficiency of solving the self-consistent field theory (SCFT) for periodic block-copolymer morphologies by combining the spectral method with Anderson mixing. Using AB diblock-copolymer melts as an example, we demonstrate that this approach can be orders of magnitude faster than competing methods, permitting precise calculations with relatively little computational cost. Moreover, our results raise significant doubts that the gyroid (G) phase extends to infinite $\chi N$. With the increased precision, we are also able to resolve subtle free-energy differences, allowing us to investigate the layer stacking in the perforated-lamellar (PL) phase and the lattice arrangement of the close-packed spherical (S$_{cp}$) phase. Furthermore, our study sheds light on the existence of the newly discovered Fddd (O$^{70}$) morphology, showing that conformational asymmetry has a significant effect on its stability.

The consumption of milk and dairy foods and the incidence of vascular disease and diabetes: An overview of the evidence

The health effects of milk and dairy food consumption would best be determined in randomised controlled trials. No adequately powered trial has been reported and none is likely because of the numbers required. The best evidence comes, therefore, from prospective cohort studies with disease events and death as outcomes. Medline was searched for prospective studies of dairy food consumption and incident vascular disease and Type 2 diabetes, based on representative population samples. Reports in which evaluation was in incident disease or death were selected. Meta-analyses of the adjusted estimates of relative risk for disease outcomes in these reports were conducted. Relevant case–control retrospective studies were also identified and the results are summarised in this article. Meta-analyses suggest a reduction in risk in the subjects with the highest dairy consumption relative to those with the lowest intake: 0.87 (0.77, 0.98) for all-cause deaths, 0.92 (0.80, 0.99) for ischaemic heart disease, 0.79 (0.68, 0.91) for stroke and 0.85 (0.75, 0.96) for incident diabetes. The number of cohort studies which give evidence on individual dairy food items is very small, but, again, there is no convincing evidence of harm from consumption of the separate food items. In conclusion, there appears to be an enormous mis-match between the evidence from long-term prospective studies and perceptions of harm from the consumption of dairy food items.

Single tap identification for fast BCI control

One of the major aims of BCI research is devoted to achieving faster and more efficient control of external devices. The identification of individual tap events in a motor imagery BCI is therefore a desirable goal. EEG is recorded from subjects performing and imagining finger taps with their left and right hands. A Differential Evolution based feature selection wrapper is used in order to identify optimal features in the spatial and frequency domains for tap identification. Channel-frequency band combinations are found which allow differentiation of tap vs. no-tap control conditions for executed and imagined taps. Left vs. right hand taps may also be differentiated with features found in this manner. A sliding time window is then used to accurately identify individual taps in the executed tap and imagined tap conditions. Highly statistically significant classification accuracies are achieved with time windows of 0.5 s and more allowing taps to be identified on a single trial basis.

A novel shape feature for fast region-based pedestrian recognition

A new class of shape features for region classification and high-level recognition is introduced. The novel Randomised Region Ray (RRR) features can be used to train binary decision trees for object category classification using an abstract representation of the scene. In particular we address the problem of human detection using an over segmented input image. We therefore do not rely on pixel values for training, instead we design and train specialised classifiers on the sparse set of semantic regions which compose the image. Thanks to the abstract nature of the input, the trained classifier has the potential to be fast and applicable to extreme imagery conditions. We demonstrate and evaluate its performance in people detection using a pedestrian dataset.

The SAFE FOODS framework for improved risk analysis of foods

Three main changes to current risk analysis processes are proposed to improve their transparency, openness, and accountability. First, the addition of a formal framing stage would allow interested parties, experts and officials to work together as needed to gain an initial shared understanding of the issue, the objectives of regulatory action, and alternative risk management measures. Second, the scope of the risk assessment is expanded to include the assessment of health and environmental benefits as well as risks, and the explicit consideration of economic- and social-impacts of risk management action and their distribution. Moreover approaches were developed for deriving improved information from genomic, proteomic and metabolomic profiling methods and for probabilistic modelling of health impacts for risk assessment purposes. Third, in an added evaluation stage, interested parties, experts, and officials may compare and weigh the risks, costs, and benefits and their distribution. As part of a set of recommendations on risk communication, we propose that reports on each stage should be made public.

Givens rotation based fast backward elimination algorithm for RBF neural network pruning

A fast backward elimination algorithm is introduced based on a QR decomposition and Givens transformations to prune radial-basis-function networks. Nodes are sequentially removed using an increment of error variance criterion. The procedure is terminated by using a prediction risk criterion so as to obtain a model structure with good generalisation properties. The algorithm can be used to postprocess radial basis centres selected using a k-means routine and, in this mode, it provides a hybrid supervised centre selection approach.