# Memristor Crossbar-Based Hardware Implementation of the IDS Method

@article{MerrikhBayat2011MemristorCH,
title={Memristor Crossbar-Based Hardware Implementation of the IDS Method},
author={F. Merrikh-Bayat and S. B. Shouraki and Ali Rohani},
journal={IEEE Transactions on Fuzzy Systems},
year={2011},
volume={19},
pages={1083-1096}
}
• Published 2011
• Computer Science
• IEEE Transactions on Fuzzy Systems
Ink drop spread (IDS) is the engine of an active learning method, which is the methodology of soft computing. IDS, as a pattern-based processing unit, extracts useful information from a system that is subjected to modeling. In spite of its excellent potential to solve problems such as classification and modeling compared with other soft-computing tools, finding its simple and fast hardware implementation is still a challenge. This paper describes a new hardware implementation of the IDS method… Expand

#### Figures and Topics from this paper

Fast IDS Computing System Method and its Memristor Crossbar-based Hardware Implementation
• Computer Science
• ArXiv
• 2016
Simpler algorithm and higher speed make the algorithm suitable for applications where real-time process, low-cost and small implementation are paramount, and reveals the effective performance of the proposed algorithm. Expand
An Optimal Hardware Implementation for Active Learning Method Based on Memristor Crossbar Structures
• Computer Science
• IEEE Systems Journal
• 2014
A fuzzy number is extracted from each IDS plane rather than from the narrow path and the spread, which leads to a significant reduction in the hardware required to implement the inference part of the algorithm and real-time computation of the implemented hardware. Expand
• Computer Science
• Neural Computing and Applications
• 2018
An abstract representation of the IDS planes is proposed which minimizes the memory requirement and the computational cost, and consequently, benefits the hardware implementation in terms of area and speed and concludes that the proposed computing structure provides a synergy between artificial neural networks and fuzzy domains. Expand
Memristive fuzzy edge detector
• Computer Science
• Journal of Real-Time Image Processing
• 2012
This paper has designed a multi-layer neuro-fuzzy computing system based on the memristor crossbar structure by introducing a new concept called the fuzzy minterm, and shows how the fuzzy XOR function can be constructed and how it can be used to extract edges from grayscale images. Expand
A novel adaptive learning algorithm for low-dimensional feature space using memristor-crossbar implementation and on-chip training
• Computer Science
• Applied Intelligence
• 2018
This 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 and can be efficiently implemented on memristor crossbar/CMOS hardware platform in terms of area and speed. Expand
The Neuro-Fuzzy Computing System With the Capacity of Implementation on a Memristor Crossbar and Optimization-Free Hardware Training
• Computer Science
• IEEE Transactions on Fuzzy Systems
• 2014
It is shown that neural networks are working in the same way as logical circuits when the connection between them is through the fuzzy logic, and a new neuro-fuzzy computing system is proposed that has the potential to be directly trained using the Hebbian learning rule and without the need for any optimization. Expand
Using a memristor crossbar structure to implement a novel adaptive real-time fuzzy modeling algorithm
• Computer Science
• Fuzzy Sets Syst.
• 2017
This study proposes a novel adaptive and real-time fuzzy modeling algorithm, which employs the active learning method concept to mimic the functionality of the brain's right hemisphere, and demonstrates that the proposed fuzzy architecture can be implemented easily and efficiently using existing crossbar structures. Expand
Efficient neuro-fuzzy system and its Memristor Crossbar-based Hardware Implementation
• Computer Science
• ArXiv
• 2011
A novel neuro-fuzzy system is proposed where its learning is based on the creation of fuzzy relations by using new implication method without utilizing any exact mathematical techniques, and this system can be a good candidate to be used for creating artificial brain. Expand
Memristive Neuro-Fuzzy System
• Computer Science, Medicine
• IEEE Transactions on Cybernetics
• 2013
Simulation results indicate that this neuro-fuzzy computing system can be a good candidate to be used for creating artificial brain and all synaptic weights in this method are always non-negative, and there is no need to adjust them precisely. Expand
Digital hardware realization of a novel adaptive ink drop spread operator and its application in modeling and classification and on-chip training
• Computer Science
• Int. J. Mach. Learn. Cybern.
• 2019
The ultimate goal in this paper was to present a hardware implementation with an on-chip training that allows it to adapt to its environment without dependency on the host system (on-chip learning). Expand

#### References

SHOWING 1-10 OF 33 REFERENCES
Mixed analog-digital crossbar-based hardware implementation of sign–sign LMS adaptive filter
• Computer Science
• 2011
This paper will propose a new mixed analog-digital circuit as a hardware implementation of the sign–sign least mean square (LMS) adaptive filter algorithm, based on the simple memristor crossbar structure. Expand
Performance of the IDS Method as a Soft Computing Tool
• Mathematics, Computer Science
• IEEE Transactions on Fuzzy Systems
• 2008
This study demonstrates that the IDS method has superior capability to function as a soft computing tool based on comparative evaluations with artificial neural networks and fuzzy inference systems. Expand
Memristor-The missing circuit element
A new two-terminal circuit element-called the memristorcharacterized by a relationship between the charge q(t)\equiv \int_{-\infty}^{t} i(\tau) d \tau and the flux-linkage \varphi(t)\equiv \int_{-Expand
A high performance IDS processing unit for a new fuzzy-based modeling
• Computer Science
• 2004 IEEE International Conference on Fuzzy Systems (IEEE Cat. No.04CH37542)
• 2004
A developed high performance IDS processing unit enables ALM-based modeling systems to increase real-time capabilities and a consideration of the redundancy of IDSprocessing units is described. Expand
SPICE modeling of memristive, memcapacitative and meminductive systems
• Computer Science
• 2009 European Conference on Circuit Theory and Design
• 2009
It is shown that the memristor, designed in HP laboratories, can be modeled as a first-order memristive system with nonlinear dependence of the time derivative of the state variable on this variable and on the current flowing through. Expand
A novel hardware implementation of IDS method
• Computer Science
• IEICE Electron. Express
• 2009
A new implementation of a hardware unit implementing the ink drop spread (IDS) method is presented, which uses a fuzzy curve fitting technique for behavior extraction or finding the input-output transformation of each of the single-input single-output systems. Expand
The missing memristor found
• Physics, Medicine
• Nature
• 2008
It is shown, using a simple analytical example, that memristance arises naturally in nanoscale systems in which solid-state electronic and ionic transport are coupled under an external bias voltage. Expand
Memristive model of amoeba’s learning
• Computer Science, Biology
• 2008
It is shown that memristive behaviour can be mapped into the response of a simple electronic circuit consisting of an LC contour and a memory-resistor (a memristor) to a train of voltage pulses that mimic environment changes. Expand
A study on the modeling ability of the IDS method: A soft computing technique using pattern-based information processing
• Computer Science
• Int. J. Approx. Reason.
• 2007
Experimental results demonstrated that the IDS method can handle various modeling targets, ranging from logic operations to complex nonlinear systems, and that its modeling performance is satisfactory in comparison with that of feedforward neural networks. Expand
Proposal for Memristors in Signal Processing
• B. Mouttet
• Engineering, Computer Science
• NanoNet
• 2008
It is proposed to combine such memristors with operational amplifier circuitry and fixed resistor elements so as to form a programmable signal processor capable of selective transmission and multiplexing of multiple signals for applications in communications and programmable drive waveform control. Expand