ABSTRACT Neural algorithms and architectures are rarely tested on actual hardware testbeds owing ... more ABSTRACT Neural algorithms and architectures are rarely tested on actual hardware testbeds owing to the high cost and long time required to develop neural chips. A Fast Prototyping Neural System FPNS where neural architectures can be easily programmed and configured on programmable chips is here presented. Two different case studies were developed and used as benchmark for our system, showing a good performance. 1 Introduction Today both academic and industrial institutions make neural chips available on the market. Academic neural chips are rarely usable: they can actually work only in the environment where they were developed . Moreover a specific experience is required to configure and program the chips. Industrial integrated circuits are more "user friendly" but they present some drawbacks: they are expensive, need a development system and they are not usually reconfigurable to new architectures or new paradigms. On the other side it is not easy to test new architectures implementing full ...
Proceedings of the International Joint Conference on Neural Networks, 2003., 2003
Pharmacokinetics (PK) studies the absorption and the elimination of drugs in the human body. Most... more Pharmacokinetics (PK) studies the absorption and the elimination of drugs in the human body. Most PK models are parametric. Once it is identified, a PK model can estimate e.g. plasma concentrations over time for a given individual. Population PK aims at making sensible predictions even when measurements are so scarce to prevent model identification. In fact those predictions integrate past
The "inverted pendulum problem" is perhaps the most widely used benchmarking study to a... more The "inverted pendulum problem" is perhaps the most widely used benchmarking study to assess the effectiveness of emerging control design techniques. In this paper the "Backpropagation Through Time" learning method is used to train a multilayer perceptron neural network to control an actual physical system, consisting in a pendulum free to pivot on a cart, which is moved by a DC motor within a space of 60 cm on a pair of slide guides. The goal of the neural controller is to maintain the inverted pendulum balanced at the middle of the slide guides. The neural network has been implemented both with a DSP and with a Fast Prototipyng Neural System (FPNS) hardware. The experimental results show the effectiveness of the used technique: the network is able to balance the pendulum also from difficult initial conditions.
IEEE International Symposium on Circuits and Systems, 1996
Automatic speech recognition is a severe application for neural networks. An ensemble of more neu... more Automatic speech recognition is a severe application for neural networks. An ensemble of more neural networks can be the keystone to increase the performance of the recognizer. Different techniques to pre-process the vocal signal are also shown. This approach is used to implement a "viva voice" recognizer for a car phone. A PC based demonstrator is available to recognize digits
A powerful goal for 3D CAD tools is today the simulation of working environments to find the ergo... more A powerful goal for 3D CAD tools is today the simulation of working environments to find the ergonomic parameters which relate people to objects in the space. Mathematical models of human movements are complex to define and hard to solve. Artificial neural systems (ANS) could be an interesting approach to the problem: why not to use artificial neurons to simulate
ABSTRACT Neural algorithms and architectures are rarely tested on actual hardware testbeds owing ... more ABSTRACT Neural algorithms and architectures are rarely tested on actual hardware testbeds owing to the high cost and long time required to develop neural chips. A Fast Prototyping Neural System FPNS where neural architectures can be easily programmed and configured on programmable chips is here presented. Two different case studies were developed and used as benchmark for our system, showing a good performance. 1 Introduction Today both academic and industrial institutions make neural chips available on the market. Academic neural chips are rarely usable: they can actually work only in the environment where they were developed . Moreover a specific experience is required to configure and program the chips. Industrial integrated circuits are more "user friendly" but they present some drawbacks: they are expensive, need a development system and they are not usually reconfigurable to new architectures or new paradigms. On the other side it is not easy to test new architectures implementing full ...
Proceedings of the International Joint Conference on Neural Networks, 2003., 2003
Pharmacokinetics (PK) studies the absorption and the elimination of drugs in the human body. Most... more Pharmacokinetics (PK) studies the absorption and the elimination of drugs in the human body. Most PK models are parametric. Once it is identified, a PK model can estimate e.g. plasma concentrations over time for a given individual. Population PK aims at making sensible predictions even when measurements are so scarce to prevent model identification. In fact those predictions integrate past
The "inverted pendulum problem" is perhaps the most widely used benchmarking study to a... more The "inverted pendulum problem" is perhaps the most widely used benchmarking study to assess the effectiveness of emerging control design techniques. In this paper the "Backpropagation Through Time" learning method is used to train a multilayer perceptron neural network to control an actual physical system, consisting in a pendulum free to pivot on a cart, which is moved by a DC motor within a space of 60 cm on a pair of slide guides. The goal of the neural controller is to maintain the inverted pendulum balanced at the middle of the slide guides. The neural network has been implemented both with a DSP and with a Fast Prototipyng Neural System (FPNS) hardware. The experimental results show the effectiveness of the used technique: the network is able to balance the pendulum also from difficult initial conditions.
IEEE International Symposium on Circuits and Systems, 1996
Automatic speech recognition is a severe application for neural networks. An ensemble of more neu... more Automatic speech recognition is a severe application for neural networks. An ensemble of more neural networks can be the keystone to increase the performance of the recognizer. Different techniques to pre-process the vocal signal are also shown. This approach is used to implement a "viva voice" recognizer for a car phone. A PC based demonstrator is available to recognize digits
A powerful goal for 3D CAD tools is today the simulation of working environments to find the ergo... more A powerful goal for 3D CAD tools is today the simulation of working environments to find the ergonomic parameters which relate people to objects in the space. Mathematical models of human movements are complex to define and hard to solve. Artificial neural systems (ANS) could be an interesting approach to the problem: why not to use artificial neurons to simulate
Uploads
Papers by E. Pasero