Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You and Your Team.

Learn More →

A novel adaptive learning algorithm for low-dimensional feature space using memristor-crossbar implementation and on-chip training

A novel adaptive learning algorithm for low-dimensional feature space using memristor-crossbar... Proposing an efficient algorithm with an appropriate hardware implementation has always been an interesting and a rather challenging field of research in Artificial Intelligence (AI). Fuzzy logic is one of the techniques that can be used for accurate and high-speed modeling as well as controlling complex and nonlinear systems. The “defuzzification” process during the test phase as well as the repetitive processes in order to find the optimal parameters during the training phase, lead to some serious limitations in real-time applications and hardware implementation of these algorithms. The proposed algorithm employs Ink Drop Spread (IDS) concept to mimic the functionality of human brain. In this algorithm, learning is based on the distance between training data and the “learning plane”. Unlike previous algorithms, the new one does not need to partition nor the input space neither the calculation of IDS plane features. Besides, the output is obtained without using the optimization methods. The proposed algorithm is a numerical foundation that does not encounter a processing problem and lack of memory in dealing with different datasets consisting of a large number of samples. This algorithm can be efficiently implemented on memristor crossbar/CMOS hardware platform in terms of area and speed. This hardware has the ability to learn and adapt to the environment regardless of a host system (on-chip learning capability). Finally, to verify the performance of the proposed algorithm, it has been compared to ALM, RBF and PNN algorithms which have a similar functionality. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Applied Intelligence Springer Journals

A novel adaptive learning algorithm for low-dimensional feature space using memristor-crossbar implementation and on-chip training

Klidbary, Sajad; Shouraki, Saeed
Applied Intelligence , Volume 48 (11) – Jun 1, 2018
Download PDF
18 pages
Read Article

Loading next page...
 
/lp/springer_journal/a-novel-adaptive-learning-algorithm-for-low-dimensional-feature-space-sEVsbSIT4J
Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer Science+Business Media, LLC, part of Springer Nature
Subject
Computer Science; Artificial Intelligence (incl. Robotics); Mechanical Engineering; Manufacturing, Machines, Tools
ISSN
0924-669X
eISSN
1573-7497
DOI
10.1007/s10489-018-1202-6
Publisher site
See Article on Publisher Site

Abstract

Proposing an efficient algorithm with an appropriate hardware implementation has always been an interesting and a rather challenging field of research in Artificial Intelligence (AI). Fuzzy logic is one of the techniques that can be used for accurate and high-speed modeling as well as controlling complex and nonlinear systems. The “defuzzification” process during the test phase as well as the repetitive processes in order to find the optimal parameters during the training phase, lead to some serious limitations in real-time applications and hardware implementation of these algorithms. The proposed algorithm employs Ink Drop Spread (IDS) concept to mimic the functionality of human brain. In this algorithm, learning is based on the distance between training data and the “learning plane”. Unlike previous algorithms, the new one does not need to partition nor the input space neither the calculation of IDS plane features. Besides, the output is obtained without using the optimization methods. The proposed algorithm is a numerical foundation that does not encounter a processing problem and lack of memory in dealing with different datasets consisting of a large number of samples. This algorithm can be efficiently implemented on memristor crossbar/CMOS hardware platform in terms of area and speed. This hardware has the ability to learn and adapt to the environment regardless of a host system (on-chip learning capability). Finally, to verify the performance of the proposed algorithm, it has been compared to ALM, RBF and PNN algorithms which have a similar functionality.

Journal

Applied Intelligence – Springer Journals

Published: Jun 1, 2018

References

  • Fuzzy systems, neural networks and neuro-fuzzy systems: a vision on their hardware implementation and platforms over two decades
    Bosque, G; del Campo, I; Echanobe, J
  • Memristor-based multilayer neural networks with online gradient descent training
    Soudry, D
  • Neural networks and statistical techniques: a review of applications
    Paliwal, M; Kumar, UA
  • Fuzzy neural network models for classification
    Kulkarni, AD; Cavanaugh, CD
  • Development and implementation of parameterized FPGA-based general purpose neural networks for online applications
    Gomperts, A; Ukil, A; Zurfluh, F
  • Neural networks for classification: a survey
    Zhang, GP
  • Artificial neural networks in hardware: a survey of two decades of progress
    Misra, J; Saha, I
  • The impact of arithmetic representation on implementing MLP-BP on FPGAs: a study
    Savich, AW; Moussa, M; Areibi, S
  • Fuzzy sets, in fuzzy sets, fuzzy logic, and fuzzy systems: selected papers by Lotfi A Zadeh
    Zadeh, LA
  • Outline of a new approach to the analysis of complex systems and decision processes
    Zadeh, LA
  • Soft computing and fuzzy logic
    Zadeh, LA
  • Fuzzy interpretation of human intelligence
    Shouraki, SB; Honda, N; Yuasa, G
  • Recursive fuzzy modeling based on fuzzy interpolation
    Shouraki, SB; Honda, N
  • Using IDS fitted Q to develop a real-time adaptive controller for dynamic resource provisioning in cloud’s virtualized environment
    Bahrpeyma, F; Zakerolhoseini, A; Haghighi, H
  • The neuro-fuzzy computing system with the capacity of implementation on a memristor crossbar and optimization-free hardware training
    Merrikh-Bayat, F; Merrikh-Bayat, F; Shouraki, SB
  • A novel density-based fuzzy clustering algorithm for low dimensional feature space
    Javadian, M; Shouraki, SB; Kourabbaslou, SS
  • Pattern analysis by active learning method classifier
    Firouzi, M; Shouraki, SB; Afrakoti, IEP
  • Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks
    Chen, T; Chen, H
  • Time series forecasting by combining RBF networks, certainty factors, and the Box-Jenkins model
    Wedding, DK; Cios, KJ
  • A local linear radial basis function neural network for financial time-series forecasting
    Nekoukar, V; Beheshti, MTH
  • Two fast and accurate heuristic RBF learning rules for data classification
    Rouhani, M; Javan, DS
  • Polynomial-based radial basis function neural networks (p-RBF NNs) and their application to pattern classification
    Park, B-J; Pedrycz, W; Oh, S-K
  • Face recognition with radial basis function (RBF) neural networks
    Er, MJ
  • An intelligent system for automated breast cancer diagnosis and prognosis using SVM based classifiers
    Maglogiannis, I; Zafiropoulos, E; Anagnostopoulos, I
  • Genetic algorithm pruning of probabilistic neural networks in medical disease estimation
    Mantzaris, D; Anastassopoulos, G; Adamopoulos, A
  • A new neural dynamic classification algorithm
    Rafiei, MH; Adeli, H
  • Palmprint recognition using fastICA algorithm and radial basis probabilistic neural network
    Shang, L
  • Improved probabilistic neural network PNN and its application to defect recognition in rock bolts
    Sun, X-Y
  • Adaptive probabilistic neural networks for pattern classification in time-varying environment
    Rutkowski, L
  • A study on the modeling ability of the IDS method: a soft computing technique using pattern-based information processing
    Murakami, M; Honda, N
  • Memristor-the missing circuit element
    Chua, L
  • Memristive devices and systems
    Chua, LO; Kang, SM
  • The missing memristor found
    Strukov, DB
  • From synapses to circuitry: Using memristive memory to explore the electronic brain
    Snider, G
  • A spintronic memristor-based neural network with radial basis function for robotic manipulator control implementation
    Li, T
  • Nanoionics-based resistive switching memories
    Waser, R; Aono, M
  • Memristive model of amoeba learning
    Pershin, YV; La Fontaine, S; Di Ventra, M
  • An improved design of RBF neural network control algorithm based on spintronic memristor crossbar array
    Li, T
  • Improved model of TiO2 memristor
    Kolka, Z; Biolek, D; Biolkova, V
  • Stochasticity modeling in memristors
    Naous, R; Al-Shedivat, M; Salama, KN
  • Reliable modeling of ideal generic memristors via state-space transformation
    Biolek, D
  • Memristor crossbar-based neuromorphic computing system: a case study
    Hu, M
  • Memristor crossbar architecture for synchronous neural networks
    Starzyk, JA
  • Using a memristor crossbar structure to implement a novel adaptive real-time fuzzy modeling algorithm
    Afrakoti, IEP
  • Memristive neuro-fuzzy system
    Merrikh-Bayat, F; Shouraki, SB
  • Artificial synapses with short-and long-term memory for spiking neural networks based on renewable materials
    Park, Y; Lee, J-S
  • Self-adaptive spike-time-dependent plasticity of metal-oxide memristors
    Prezioso, M
  • Memristor crossbar-based hardware implementation of the IDS method
    Merrikh-Bayat, F; Shouraki, SB; Rohani, A
  • An optimal hardware implementation for active learning method based on memristor crossbar structures
    Afrakoti, IEP; Shouraki, SB; Haghighat, B
  • Regression modeling in back-propagation and projection pursuit learning
    Hwang, J-N
  • Objective functions for training new hidden units in constructive neural networks
    Kwok, T-Y; Yeung, D-Y
  • Constructive feedforward neural networks using Hermite polynomial activation functions
    Ma, L; Khorasani, K
  • ANFIS: adaptive-network-based fuzzy inference system
    Jang, J-S