A Novel Hardware Systolic Architecture of a Self-Organizing Map Neural Network

Khalifa, Khaled Ben; Blaiech, Ahmed Ghazi; Bedoui, Mohamed Hédi

doi:10.1155/2019/8212867

Cited by 9 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SOM is made up of a single layer of neurons in one (1D) or two-dimensional (2D) grid (Ben et al ., 2019). Each neuron on the grid represents an n-dimensional weight vector where n is the dimension of the input data to the SOM network.…”

Section: Key Technologies and Architecturesmentioning

confidence: 99%

Deep learning for SDN-enabled campus networks: proposed solutions, challenges and future directions

Chanhemo

Mohsini

Mjahidi

et al. 2023

IJICC

View full text Add to dashboard Cite

PurposeThis study explores challenges facing the applicability of deep learning (DL) in software-defined networks (SDN) based campus networks. The study intensively explains the automation problem that exists in traditional campus networks and how SDN and DL can provide mitigating solutions. It further highlights some challenges which need to be addressed in order to successfully implement SDN and DL in campus networks to make them better than traditional networks.Design/methodology/approachThe study uses a systematic literature review. Studies on DL relevant to campus networks have been presented for different use cases. Their limitations are given out for further research.FindingsFollowing the analysis of the selected studies, it showed that the availability of specific training datasets for campus networks, SDN and DL interfacing and integration in production networks are key issues that must be addressed to successfully deploy DL in SDN-enabled campus networks.Originality/valueThis study reports on challenges associated with implementation of SDN and DL models in campus networks. It contributes towards further thinking and architecting of proposed SDN-based DL solutions for campus networks. It highlights that single problem-based solutions are harder to implement and unlikely to be adopted in production networks.

show abstract

Section: Key Technologies and Architecturesmentioning

confidence: 99%

Deep learning for SDN-enabled campus networks: proposed solutions, challenges and future directions

Chanhemo

Mohsini

Mjahidi

et al. 2023

IJICC

View full text Add to dashboard Cite

show abstract

“…In addition, hardware implemented ANNs allow for specific optimization of the structure of particular components. This leads to a significant reduction in energy consumption and the device miniaturization that translates into cost reduction [19,[21][22][23][24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

An Energy-Efficient, Parallel Neighborhood and Adaptation Functions for Hardware Implemented Self-Organizing Maps Applied in Smart Grid

Kolasa

2020

Energies

View full text Add to dashboard Cite

Smart Grids (SGs) can be successfully supported by Wireless Sensor Networks (WSNs), especially through these consisting of intelligent sensors, which are able to efficiently process the still growing amount of data. We propose a contribution to the development of such intelligent sensors, which in an advanced version can be equipped with embedded low-power artificial neural networks (ANNs), supporting the analysis and the classification of collected data. This approach allows to reduce the energy consumed by particular sensors during the communication with other nodes of a larger WSN. This in turn, facilitates the maintenance of a net of such sensors, which is a paramount feature in case of their application in SG devices distributed over a large area. In this work, we focus on a novel, energy-efficient neighborhood mechanism (NM) with the neighborhood function (NF). This mechanism belongs to main components of self learning ANNs. We propose a realization of this component as a specialized chip in the CMOS technology and its optimization in terms of the circuit complexity and the consumed energy. The circuit was realized as a prototype chip in the CMOS 130 nm technology, and verified by means of transistor level simulations and measurements.

show abstract

“…A new modular architecture for a SOM called systolic-SOM (SSOM) which is based on the use of a generic model inspired by a systolic movement was proposed by Khalifa et al [24]. The model was formed by two levels of nested parallelism of neurons and connections that provided a distributed set of independent computations between the processing units.…”

mentioning

confidence: 99%

Hardware Self-Organizing Map Based on Digital Frequency-Locked Loop and Triangular Neighborhood Function

Hikawa

2021

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

This paper proposes a unique hardware architecture for a self-organizing map (SOM) that mimics the biological brain by using pulse mode operation. In the proposed SOM, vector elements are given as in the form of frequency modulated signals, and digital frequency-locked loops (DFLLs) in neurons handle the computations of the vector elements. The SOM is trained by unsupervised learning, where the winner neuron that has the nearest weight vector is found first. In the proposed SOM, the winner neuron is found by counting cycle slips between the signals that carry input and weight vectors. After the winner neuron is found, weight vectors selected by a neighborhood function are updated toward the input vector. Triangular neighborhood function that is implemented by using an attenuating enable signal for the DFLLs, is employed. To evaluate the proposed SOM and its building components, VHDL simulations and experiments using an FPGA were conducted. Compared to the previous work, the operation speed and learning capability were significantly improved. Novelty of the proposed architecture is it uniquely uses a pulse-based operation that mimics the biological brain, and it was verified that unsupervised learning can be realized with neurons communicating with each other using frequency modulated pulse signals.

show abstract

A Novel Hardware Systolic Architecture of a Self-Organizing Map Neural Network

Cited by 9 publications

References 21 publications

Deep learning for SDN-enabled campus networks: proposed solutions, challenges and future directions

Deep learning for SDN-enabled campus networks: proposed solutions, challenges and future directions

An Energy-Efficient, Parallel Neighborhood and Adaptation Functions for Hardware Implemented Self-Organizing Maps Applied in Smart Grid

Hardware Self-Organizing Map Based on Digital Frequency-Locked Loop and Triangular Neighborhood Function

Contact Info

Product

Resources

About