Problem Description: It should be well known that processors are outstripping memory performance: specifically that memory latencies are not improving as fast as processor cycle time or IPC or memory bandwidth. Thought experiment: imagine that a cache miss takes 10000 cycles to execute. For such a processor instruction level parallelism is useless, because most of the time is spent waiting for ...

Backpropagation based on minimization algorithms is replaced by heuristic search techniques for quantized weights. The resulting algorithm is fast, avoids local minima of the cost function, and may be used either as initialization method for standard backpropagation or as a logical rule extraction technique.

One of the major research thrusts in the speech group at ICSI is to use Multi-Layer Perceptron (MLP) based features in automatic speech recognition (ASR). This paper presents a study of three aspects of this effort: 1) the properties of the MLP features which make them useful, 2) incorporating MLP features together with PLP features in ASR, and 3) possible redundancy between MLP features and mo...

In this paper, a channel estimator based on an adaptive neuro fuzzy inference system (ANFIS) is proposed for the purpose of estimating channel frequency responses in orthogonal frequency division multiplexing-interleave division multiple access (OFDM-IDMA) systems. To see the performance of our proposed channel estimation method, five different techniques including well-known pilot-based estima...

In this paper, it is shown that Multilayer perceptron Neural Network can elegantly perform nonlinear regression of transfer characteristic of electronic devices. After rigorous computer simulations authors develop the optimal MLP NN models, which elegantly perform such a nonlinear regression. Results show that the proposed optimal MLP NN models have optimal values of MSE (mean square error), r ...

BACKGROUND Emergency department (ED) visits in the US have risen dramatically over the past 2 decades. In order to meet the growing demand, mid-level providers (MLPs) - both physician assistants (PAs) and nurse practitioners (NPs) - were introduced into emergency care. Our objective was to test the hypothesis that MLP usage in US EDs continues to rise. FINDINGS We analyzed ED data from the Na...

Threads experiencing long-latency loads on a simultaneous multithreading (SMT) processor may clog shared processor resources without making forward progress, thereby starving other threads and reducing overall system throughput. An elegant solution to the long-latency load problem in SMT processors is to employ runahead execution. Runahead threads do not block commit on a longlatency load but i...

The prediction and estimation of suspended sediment concentration are investigated by using multi-layer perceptrons (MLP). The fastest MLP training algorithm, that is the Levenberg-Marquardt algorithm, is used for optimization of the network weights for data from two stations on the Tongue River in Montana, USA. The first part of the study deals with prediction and estimation of upstream and do...

Network in network (NiN) is an effective instance and an important extension of deep convolutional neural network consisting of alternating convolutional layers and pooling layers. Instead of using a linear filter for convolution, NiN utilizes shallow multilayer perceptron (MLP), a nonlinear function, to replace the linear filter. Because of the powerfulness of MLP and 1 x 1 convolutions in spa...