We present a novel layerwise optimization algorithm for the learning objective of Piecewise-Linear Convolutional Neural Networks (PL-CNNs), a large class of convolutional neural networks. Specifically, PL-CNNs employ piecewise linear non-linearities such as the commonly used ReLU and max-pool, and an SVM classifier as the final layer. The key observation of our approach is that the problem corr...

In engineering, flood routing is an important technique necessary for the solution of a floodcontrol problem and for the satisfactory operation of a flood-prediction service. A simple conceptual model like the Muskingum model is very effective for the flood routing process. One challenge in application of the Muskingum model is that its parameters cannot be measured physically. In this article ...

Many applications, e.g. in control theory and optimization depend on time– consuming parameter studies of parametrized evolution equations. Reduced basis methods are an approach to reduce the computation time of numerical simulations for these problems. The methods have gained popularity for model reduction of different numerical schemes with remarkable results preferably for scalar and linear ...

Parameter identification of system models is a fundamental step in the process of designing a controller for a system. In control engineering, a wide selection of analytic identification techniques exists for linear systems, but not for non-linear systems. Instead, the model parameters may be determined by an optimization algorithm by minimizing the error between model output and measured data....

In medium to low bit rate speech codecs the speech signal is represented by a set of parameters. The most important concept is presently Code Excited Linear Predictive (CELP) coding. A speech segment of typically 10 to 20ms is described in terms of prediction coefficients, gain factors and excitation vectors. Due to the high compression rates (0.5-1.5 bits per speech sample) the parameters are ...

the heat and mass transfer analysis for mhd casson fluid boundary layer flow over a permeable stretching sheet through a porous medium is carried out. the effect of non-uniform heat generation/absorption and chemical reaction are considered in heat and mass transport equations correspondingly. the heat transfer analysis has been carried out for two different heating processes namely; the prescr...

The presence of several nonlinear analog circuits and Micro-Electro-Mechanical (MEM) components in modern mixed signal System-on-Chips (SoC) makes the fully automatic synthesis and optimization of such systems an extremely challenging task. The research presented in this thesis concerns the development of techniques for generating Parameterized Reduced Order Models (PROMs) of nonlinear dynamica...