Applying non-ideal mixed analog-digital multipliers in electronic processing circuits based on neural networks

Lajusticia, C.; Medrano, N.; Zatorre, G.; Martin, Ben

doi:10.1109/etfa.2003.1248722

Cited by 11 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of the high accuracy of digital storage in register-based structures, the combination of both analogue and digital electronic approaches can improve the system features. Previous works [2], [3] presented the use of mixed-mode multipliers in adaptive processor implementation, showing promising results when applied to real problems.…”

Section: Introductionmentioning

confidence: 98%

Analysis and Simulation of a Mixed-Mode Neuron Architecture for Sensor Conditioning

Zatorre-Navarro

Marques

Celma-Pueyo

2006

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

The design, analysis, and system simulation of an adaptive processor based on a current-mode mixed analog-digital circuit is presented. The processor consists of a mixed four-quadrant multiplier and a current conveyor that performs the nonlinearity. Schematics, circuit parameters, and a high-level model are shown. The results achieved when applying this processor model to conditioning several sensor types are discussed.

show abstract

Section: Introductionmentioning

confidence: 98%

Analysis and Simulation of a Mixed-Mode Neuron Architecture for Sensor Conditioning

Zatorre-Navarro

Marques

Celma-Pueyo

2006

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

show abstract

“…Because of the high accuracy of digital storage in register-based structures, the combination of both analogue and digital electronics can improve the system features. Previous works [2] [3] presented the use of mixedmode multipliers to implement adaptive processors, showing promising results when applied to realistic problems.…”

Section: Introductionmentioning

confidence: 99%

An adaptive circuit for low-power sensor processing: Mismatch effects

Medrano

Sanz

Martínez

et al. 2007

2007 18th European Conference on Circuit Theory and Design

Self Cite

View full text Add to dashboard Cite

This paper presents a study of mismatch effects in a digitally programmable analogue processor designed for small embedded applications. Circuit programmability allows for its adaptation to deviations in circuit operation or environmental effects. Starting from circuit simulation data, the system-level operation is modelled, showing its robustness to circuit mismatch. Simulation results of the proposed processor applied to compensate the response of a sinusoidal sensor and its robustness to mismatch are presented.

show abstract

“…Due to the high accuracy of digital storage in register-based structures, the combination of both analog and digital can improve system performance. Previous works [3] presented the use of mixedmode multipliers in artificial neuron implementation, showing promising results applied to real problems. This paper presents the analysis and simulation of a current-mode based ANN with digital weight storage and its application to the linearization of a Giant Magneto-Resistive (GMR) sensor.…”

Section: Introductionmentioning

confidence: 97%

Mixed-Mode Artificial Neuron for CMOS Integration

Zatorre

Medrano

Sanz

et al.

MELECON 2006 - 2006 IEEE Mediterranean Electrotechnical Conference

Self Cite

View full text Add to dashboard Cite

A new approach to designing artificial neurons in CMOS technology is proposed in this paper. Design and simulation results of the basic building blocks are presented. Programmable weights are obtained using a current-mode mixed-signal four-quadrant multiplier, whereas the non-linear output function is implemented with a specifically designed class AB current conveyor. Starting from circuit simulation results, the behaviour of the proposed neuron was modeled. A Multilayer Perceptron Network implemented with the new artificial neuron structure was trained to tackle linearization of a Giant Magneto-Resistive sensor. Simulation results show the efficiency of the new implementation.

show abstract

Applying non-ideal mixed analog-digital multipliers in electronic processing circuits based on neural networks

Cited by 11 publications

References 11 publications

Analysis and Simulation of a Mixed-Mode Neuron Architecture for Sensor Conditioning

Analysis and Simulation of a Mixed-Mode Neuron Architecture for Sensor Conditioning

An adaptive circuit for low-power sensor processing: Mismatch effects

Mixed-Mode Artificial Neuron for CMOS Integration

Contact Info

Product

Resources

About