A new digital pulse-mode neuron with adjustable activation function
IEEE Transactions on Neural NetworksPublished 1 January 2003
Hiroomi Hikawa
Citations39
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A new pulse-mode digital neuron which is based on voting neuron is described, which provides adjustable nonlinear function, which resembles the sigmoid function.
Abstract
This paper describes a new pulse-mode digital neuron which is based on voting neuron. The signal level of the neuron is represented by frequency of pulse signals. The proposed neuron provides adjustable nonlinear function, which resembles the sigmoid function. The proposed neuron and experimental multilayer neural network (MNN) are implemented on field programmable gate array (FPGA) and various experiments are conducted to test the performance of the proposed system. The experimental results show that the proposed neuron has rigid adjustable nonlinear function.
Keywords
Computer SciencePhysics and Astronomy
NatureLearning representations by back-propagating errors
30,885 Citations1986David E. Rumelhart, Geoffrey E. Hinton +1 more
Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Control Engineering PracticeDigital neural networks
478 Citations1994
This chapter discusses the development of unsupervised networks for association/Classification and their applications in neural nets, as well as some of the techniques used in conventional optimization techniques.
IEEE Transactions on Neural NetworksPattern recognition via synchronization in phase-locked loop neural networks
406 Citations2000Frank C. Hoppensteadt, Eugene M. Izhikevich
A novel architecture of an oscillatory neural network that consists of phase-locked loop (PLL) circuits that stores and retrieves complex oscillatory patterns as synchronized states with appropriate phase relations between neurons is proposed.
IEEE Transactions on Neural NetworksFrequency-based multilayer neural network with on-chip learning and enhanced neuron characteristics
65 Citations1999Hiroomi Hikawa
Simple and modular structure of the proposed MNN leads to a massive parallel and flexible network architecture, which is well suited for very large scale integration (VLSI) implementation.
IEEE Transactions on Circuits and Systems II Analog and Digital Signal ProcessingA performance analysis of pulse stream neural and fuzzy computing systems
54 Citations1995Leonardo Reyneri
It is shown that pulse stream systems are comparable with analog systems in terms of size, and comparable with both analog and digital systems in Terms of speed, and they have both a lower power dissipation and a lower computation energy figure than digital systems.
IEEE Transactions on Neural NetworksArchitecture and statistical model of a pulse-mode digital multilayer neural network
46 Citations1995Young‐Chul Kim, M.A. Shanblatt
A new architecture and a statistical model for a pulse-mode digital multilayer neural network (DMNN) are presented, which leads to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation.
IEEE Transactions on Neural NetworksRandom noise effects in pulse-mode digital multilayer neural networks
32 Citations1995Youngchul Kim, M.A. Shanblatt
A pulse-mode digital multilayer neural network (DMNN) based on stochastic computing techniques is implemented with simple logic gates as basic computing elements and a statistical model successfully predicts the accuracy of the operations performed in the DMNN.
IEEE Transactions on Circuits and Systems I Fundamental Theory and ApplicationsA DTCNN universal machine based on highly parallel 2-D cellular automata CAM/sup 2/
22 Citations1998Takeshi Ikenaga, Takeshi Ogura
A DTCNN processing method based on a highly parallel two-dimensional (2-D) cellular automata called CAM/sup 2/ is proposed, which can attain pixel-order parallelism on a single PC board because it is composed of a content addressable memory (CAM).
Hardware implementation of a PCA learning network by an asynchronous PDM digital circuit
13 Citations2000Yuichiro Hirai, Kazuhisa Nishizawa
A PCA (principal component analysis learning network) is fabricated in a FPGA (field programmable gate array) by using an asynchronous PDM (pulse density modulation) digital circuit to solve the generalized Hebbian algorithm.
IEEE Transactions on Neural NetworksAn accelerator for neural networks with pulse-coded model neurons
12 Citations1999G.A. Frank, G. Hartmann +2 more
An accelerator is developed for a special version of the French and Stein neurons with modulatory inputs which are advantageous for simulation of synchronization mechanisms and provides a Hebbian-like learning rule and supports adaptivity.
FPGA implementation of a pulse density neural network using simultaneous perturbation
7 Citations2000Yutaka Maeda, T. Tada
A FPGA implementation of a pulse density neural network circuit with learning ability is described, adopting the simultaneous perturbation method as a learning rule of the implementation.
Learning performance of frequency-modulation digital neural network with on-chip learning
5 Citations2002Hiroomi Hikawa
The proposed MNN architecture was implemented on field programmable gate arrays and various experiments were conducted to test the performance of the system, which showed that the proposed neuron has good learning performance and generalization capabilities.