Applicability of approximate multipliers in hardware neural networks

Authors:
Uroš Lotrič;Patricio Bulić
Affiliations:
University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia;University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia
Venue:
Neurocomputing
Year:
2012

Citing 14
Cited 1

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Finite Precision Error Analysis of Neural Network Hardware Implementations

IEEE Transactions on Computers
Circuit Design with VHDL

Circuit Design with VHDL
Improving Accuracy in Mitchell's Logarithmic Multiplication Using Operand Decomposition

IEEE Transactions on Computers
Statistical Comparisons of Classifiers over Multiple Data Sets

The Journal of Machine Learning Research
A high bit resolution FPGA implementation of a FNN with a new algorithm for the activation function

Neurocomputing
A support vector machine with integer parameters

Neurocomputing
Dynamic MAC-based architecture of artificial neural networks suitable for hardware implementation on FPGAs

Neurocomputing
Artificial neural networks: a review of commercial hardware

Engineering Applications of Artificial Intelligence
Truncated binary multipliers with variable correction and minimum mean square error

IEEE Transactions on Circuits and Systems Part I: Regular Papers
Artificial neural networks in hardware: A survey of two decades of progress

Neurocomputing
An iterative logarithmic multiplier

Microprocessors & Microsystems
Behavioral simulation and synthesis of biological neuron systems using synthesizable VHDL

Neurocomputing
Logarithmic multiplier in hardware implementation of neural networks

ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part I

An approximate logarithmic squaring circuit with error compensation for DSP applications

Microelectronics Journal

Quantified Score

Hi-index	0.01

Visualization

Abstract

In recent years there has been a growing interest in hardware neural networks, which express many benefits over conventional software models, mainly in applications where speed, cost, reliability, or energy efficiency are of great importance. These hardware neural networks require many resource-, power- and time-consuming multiplication operations, thus special care must be taken during their design. Since the neural network processing can be performed in parallel, there is usually a requirement for designs with as many concurrent multiplication circuits as possible. One option to achieve this goal is to replace the complex exact multiplying circuits with simpler, approximate ones. The present work demonstrates the application of approximate multiplying circuits in the design of a feed-forward neural network model with on-chip learning ability. The experiments performed on a heterogeneous Proben1 benchmark dataset show that the adaptive nature of the neural network model successfully compensates for the calculation errors of the approximate multiplying circuits. At the same time, the proposed designs also profit from more computing power and increased energy efficiency.