1# Library to Find Best eBook for Read
Author : Georg Wilckens
Release : 2013
Genre :
Kind : eBook
Book Rating : 692/5 ( reviews)
Book Synopsis A New Perspective on Analog-to-digital Conversion of Continuous-time Signals by : Georg Wilckens
Download or read book A New Perspective on Analog-to-digital Conversion of Continuous-time Signals written by Georg Wilckens. This book was released on 2013. Available in PDF, EPUB and Kindle. Book excerpt:
Author : Patrick Murer
Release : 2022-05-13
Genre : Computers
Kind : eBook
Book Rating : 585/5 ( reviews)
Book Synopsis A New Perspective on Memorization in Recurrent Networks of Spiking Neurons by : Patrick Murer
Download or read book A New Perspective on Memorization in Recurrent Networks of Spiking Neurons written by Patrick Murer. This book was released on 2022-05-13. Available in PDF, EPUB and Kindle. Book excerpt: This thesis studies the capability of spiking recurrent neural network models to memorize dynamical pulse patterns (or firing signals). In the first part, discrete-time firing signals (or firing sequences) are considered. A recurrent network model, consisting of neurons with bounded disturbance, is introduced to analyze (simple) local learning. Two modes of learning/memorization are considered: The first mode is strictly online, with a single pass through the data, while the second mode uses multiple passes through the data. In both modes, the learning is strictly local (quasi-Hebbian): At any given time step, only the weights between the neurons firing (or supposed to be firing) at the previous time step and those firing (or supposed to be firing) at the present time step are modified. The main result is an upper bound on the probability that the single-pass memorization is not perfect. It follows that the memorization capacity in this mode asymptotically scales like that of the classical Hopfield model (which, in contrast, memorizes static patterns). However, multiple-rounds memorization is shown to achieve a higher capacity with an asymptotically nonvanishing number of bits per connection/synapse. These mathematical findings may be helpful for understanding the functionality of short-term memory and long-term memory in neuroscience. In the second part, firing signals in continuous-time are studied. It is shown how firing signals, containing firings only on a regular time grid, can be (robustly) memorized with a recurrent network model. In principle, the corresponding weights are obtained by supervised (quasi-Hebbian) multi-pass learning. The asymptotic memorization capacity is a nonvanishing number measured in bits per connection/synapse as its discrete-time analogon. Furthermore, the timing robustness of the memorized firing signals is investigated for different disturbance models. The regime of disturbances, where the relative occurrence-time of the firings is preserved over a long time span, is elaborated for the various disturbance models. The proposed models have the potential for energy efficient self-timed neuromorphic hardware implementations.
Author : Marcel J.M. Pelgrom
Release : 2010-07-24
Genre : Technology & Engineering
Kind : eBook
Book Rating : 881/5 ( reviews)
Book Synopsis Analog-to-Digital Conversion by : Marcel J.M. Pelgrom
Download or read book Analog-to-Digital Conversion written by Marcel J.M. Pelgrom. This book was released on 2010-07-24. Available in PDF, EPUB and Kindle. Book excerpt: A book is like a window that allows you to look into the world. The window is shaped by the author and that makes that every window presents a unique view of the world. This is certainly true for this book. It is shaped by the topics and the projects throughout my career. Even more so, this book re?ects my own style of working and thinking. That starts already in Chap. 2. When I joined Philips Research in 1979, many of my colleagues used little paper notebooks to keep track of the most used equations and other practical things. This notebook was the beginning for Chap. 2: a collection of topics that form the basis for much of the other chapters. Chapter2 is not intended to explain these topics, but to refresh your knowledge and help you when you need some basics to solve more complex issues. In the chapters discussing the fundamental processes of conversion, you will r- ognize my preoccupation with mathematics. I really enjoy ?nding an equation that properly describes the underlying mechanism. Nevertheless mathematics is not a goalonitsown:theequationshelptounderstandthewaythevariablesareconnected to the result. Real insight comes from understanding the physics and electronics. In the chapters on circuit design I have tried to reduce the circuit diagrams to the s- plest form, but not simpler. . . I do have private opinions on what works and what should not be applied.
Author : Elizabeth Ren
Release : 2023-05-26
Genre : Computers
Kind : eBook
Book Rating : 925/5 ( reviews)
Book Synopsis Using Local State Space Model Approximation for Fundamental Signal Analysis Tasks by : Elizabeth Ren
Download or read book Using Local State Space Model Approximation for Fundamental Signal Analysis Tasks written by Elizabeth Ren. This book was released on 2023-05-26. Available in PDF, EPUB and Kindle. Book excerpt: With increasing availability of computation power, digital signal analysis algorithms have the potential of evolving from the common framewise operational method to samplewise operations which offer more precision in time. This thesis discusses a set of methods with samplewise operations: local signal approximation via Recursive Least Squares (RLS) where a mathematical model is fit to the signal within a sliding window at each sample. Thereby both the signal models and cost windows are generated by Autonomous Linear State Space Models (ALSSMs). The modeling capability of ALSSMs is vast, as they can model exponentials, polynomials and sinusoidal functions as well as any linear and multiplicative combination thereof. The fitting method offers efficient recursions, subsample precision by way of the signal model and additional goodness of fit measures based on the recursively computed fitting cost. Classical methods such as standard Savitzky-Golay (SG) smoothing filters and the Short-Time Fourier Transform (STFT) are united under a common framework. First, we complete the existing framework. The ALSSM parameterization and RLS recursions are provided for a general function. The solution of the fit parameters for different constraint problems are reviewed. Moreover, feature extraction from both the fit parameters and the cost is detailed as well as examples of their use. In particular, we introduce terminology to analyze the fitting problem from the perspective of projection to a local Hilbert space and as a linear filter. Analytical rules are given for computation of the equivalent filter response and the steady-state precision matrix of the cost. After establishing the local approximation framework, we further discuss two classes of signal models in particular, namely polynomial and sinusoidal functions. The signal models are complementary, as by nature, polynomials are suited for time-domain description of signals while sinusoids are suited for the frequency-domain. For local approximation of polynomials, we derive analytical expressions for the steady-state covariance matrix and the linear filter of the coefficients based on the theory of orthogonal polynomial bases. We then discuss the fundamental application of smoothing filters based on local polynomial approximation. We generalize standard SG filters to any ALSSM window and introduce a novel class of smoothing filters based on polynomial fitting to running sums.
Author : Raphael Urs Keusch
Release : 2022-08-19
Genre : Computers
Kind : eBook
Book Rating : 682/5 ( reviews)
Book Synopsis Composite NUV Priors and Applications by : Raphael Urs Keusch
Download or read book Composite NUV Priors and Applications written by Raphael Urs Keusch. This book was released on 2022-08-19. Available in PDF, EPUB and Kindle. Book excerpt: Normal with unknown variance (NUV) priors are a central idea of sparse Bayesian learning and allow variational representations of non-Gaussian priors. More specifically, such variational representations can be seen as parameterized Gaussians, wherein the parameters are generally unknown. The advantage is apparent: for fixed parameters, NUV priors are Gaussian, and hence computationally compatible with Gaussian models. Moreover, working with (linear-)Gaussian models is particularly attractive since the Gaussian distribution is closed under affine transformations, marginalization, and conditioning. Interestingly, the variational representation proves to be rather universal than restrictive: many common sparsity-promoting priors (among them, in particular, the Laplace prior) can be represented in this manner. In estimation problems, parameters or variables of the underlying model are often subject to constraints (e.g., discrete-level constraints). Such constraints cannot adequately be represented by linear-Gaussian models and generally require special treatment. To handle such constraints within a linear-Gaussian setting, we extend the idea of NUV priors beyond its original use for sparsity. In particular, we study compositions of existing NUV priors, referred to as composite NUV priors, and show that many commonly used model constraints can be represented in this way.
