1,721,200 research outputs found
Smart Adaptive Systems: State of the Art and Future Directions of Research
No full textThis talk outIines sorne ofthe ideas and discussions carried on by RTD-SAS researchers during the first year of the EUNITE network. The focus is mainly on theoretical aspects of Smart Adaptive Systems that will serve as the basis for the creation of successful applications. Smart Adaptive Systems are of paramount importance in many application fields, where a changing environment is a common issue, but also extremely appealing, and equally challenging, from a theoretical point of view. Here, a first attempt to highlight sorne of the current knowledge on this field and, hopefully, to give a guideline for future research directions is reported
Neural network learning for analog VLSI implementations of support vector machines: a survey
No full textIn the last few years several kinds of recurrent neural networks (RNNs) have been proposed for solving linear and nonlinear optimization problems. In this paper, we provide a survey of RNNs
that can be used to solve both the constrained quadratic optimization problem related to support vector machine (SVM) learning, and the SVM model selection by automatic hyperparameter tuning. The appeal of this approach is the possibility of implementing such networks on analog VLSI systems with relative easiness. We review several proposals appeared so far in the literature and test their behavior when applied to solve a telecommunication application, where a special purpose adaptive hardware is of great interest
The Effects of Quantization on Support Vector Machines with Gaussian Kernel
No full textWe apply here a probabilistic method to predict the
effect of quantizing the parameters of a Support Vector Machine.
Thank to the particular structure of the SVM, the dependency
of the output from the quantization noise can be predicted with
good accuracy, and a simple closed–form formula can be derived,
without imposing any hard–to–verify assumptio
Perspectives on dedicated hardware implementations
No full textAlgorithms, applications and hardware implementations of
neural networks are not investigated in close connection. Researchers working in the development of dedicated hardware implementations develop simplified versions of otherwise complex neural algorithms or develop dedicated algorithms: usually these algorithms have not been horoughly tested on real-world applications. At the same time, many theoretically sound algorithms are not feasible in dedicated hardware, therefore limiting their success only to applications where a software solution on a general-purpose system is feasible. The paper focuses on the issues related to the hardware implementation of neural algorithms and architectures and their successful application to real world-problems
Improved Neural Network for SVM Learning
No full textThe recurrent network of Xia et al. was proposed for solving
quadratic programming problems and was recently adapted to support
vector machine (SVM) learning by Tan et al.We show that this formulation contains some unnecessary circuit which, furthermore, can fail to provide the correct value of one of the SVM parameters and suggest how to avoid these drawbacks
European Symposium on Artificial Neural Networks 2001
No full textAlgorithms, applications and hardware implementations of
neural networks are not investigated in close connection. Researchers
working in the development of dedicated hardware implementations de-
velop simplied versions of otherwise complex neural algorithms or de-
velop dedicated algorithms: usually these algorithms have not been thor-
oughly tested on real-world applications. At the same time, many theo-
retically sound algorithms are not feasible in dedicated hardware, there-
fore limiting their success only to applications where a software solution
on a general-purpose system is feasible. The paper focuses on the is-
sues related to the hardware implementation of neural algorithms and
architectures and their successful application to real world-problems
Towards analog and digital hardware for support vector machines
No full textSupport Vector Machines are gaining more and more acceptance thanks to their success in many real-world problems. We propose in this work a solution for implementing SVM in hardware. The main idea is to use
a recurrent network for SVM learning that guarantees the globally convergence to the optimal solution without the use of penalty terms. This network improves our and other authors' previous solutions. The recurrent network is suitable for a straightforward analog VLSI realization; the digital solution can be derived through a discretization (in time) of the circuit
Mixing floating- and fixed-point formats for neural network learning on neuroprocessors
No full textWe examine the efficient implementation of back-propagation (BP) type algorithms on T0, a vector processor with a fixed-point engine, designed for neural network simulation. Using Matrix Back Propagation (MBP) we achieve an asymptotically optimal performance on T0 (about 0.8 GOPS) for both forward and backward phases, which is not possible with the standard on-line BP algorithm. We use a mixture of fixed- and floating-point operations in order to guarantee both high efficiency and fast convergence. Though the most expensive computations are implemented in fixed-point, we achieve a rate of convergence that is comparable to the floating-point version. The time taken for conversion between fixed- and floating-point is also shown to be reasonably low
- …
