Implementation of Analog Perceptron as an Essential Element of Configurable Neural Networks

Geng, Chao; Sun, Qingji; Nakatake, Shigetoshi

doi:10.3390/s20154222

Cited by 4 publications

(3 citation statements)

References 47 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Self-associative neural networks (SANNs), usually in the form of linear networks or MLP (multilayer perceptron), have a specific topology. These networks are characterized by an identical number of neurons in both the input and output layers [ 22 , 23 ]. They are therefore intended to reproduce on their outputs the values given at the input.…”

Section: Methodsmentioning

confidence: 99%

Neural Reduction of Image Data in Order to Determine the Quality of Malting Barley

Boniecki

Raba

Pilarska

et al. 2021

Sensors

View full text Add to dashboard Cite

Image analysis using neural modeling is one of the most dynamically developing methods employing artificial intelligence. The feature that caused such widespread use of this technique is mostly the ability of automatic generalization of scientific knowledge as well as the possibility of parallel analysis of the empirical data. A properly conducted learning process of artificial neural network (ANN) allows the classification of new, unknown data, which helps to increase the efficiency of the generated models in practice. Neural image analysis is a method that allows extracting information carried in the form of digital images. The paper focuses on the determination of imperfections such as contaminations and damages in the malting barley grains on the basis of information encoded in the graphic form represented by the digital photographs of kernels. This choice was dictated by the current state of knowledge regarding the classification of contamination that uses undesirable features of kernels to exclude them from use in the malting industry. Currently, a qualitative assessment of kernels is carried by malthouse-certified employees acting as experts. Contaminants are separated from a sample of malting barley manually, and the percentages of previously defined groups of contaminations are calculated. The analysis of the problem indicates a lack of effective methods of identifying the quality of barley kernels, such as the use of information technology. There are new possibilities of using modern methods of artificial intelligence (such as neural image analysis) for the determination of impurities in malting barley. However, there is the problem of effective compression of graphic data to a form acceptable for ANN simulators. The aim of the work is to develop an effective procedure of graphical data compression supporting the qualitative assessment of malting barley with the use of modern information technologies. Image analysis can be implemented into dedicated software.

show abstract

Section: Methodsmentioning

confidence: 99%

Neural Reduction of Image Data in Order to Determine the Quality of Malting Barley

Boniecki

Raba

Pilarska

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Another interesting feature of source followers is that its characteristics are similar to a rectified linear activation unit (ReLU) used as an activation function in neural network [54,55]. In conventional ReLU, the output corresponding to the input x is given by 0 for negative x and increases by a slope of unity for positive x, which is similar to the source follower V s -V g characteristics with V th = 0 and large V d .…”

Section: Activation Function In Neural Networkmentioning

confidence: 99%

Ferroelectric source follower for voltage-sensing nonvolatile memory and computing-in-memory

Toprasertpong

Matsui

Takenaka

et al. 2023

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

Memory arrays and computing-in-memory architecture based on emerging nonvolatile memory devices with a current-sensing scheme face several challenges when implemented in large-scale arrays, such as power and area penalties, voltage drop, and power-source limitation. Here, we demonstrate ferroelectric source followers as nonvolatile memory devices operating with a voltage-sensing scheme. The voltage output read out from the source terminal of a ferroelectric field-effect transistor is determined in a nonvolatile manner by the polarization state stored in a ferroelectric gate insulator, giving a higher output voltage at a lower threshold voltage. Device modeling reveals that the output voltage is described by a simple expression of the threshold voltage, gate bias, drain bias, and body-effect factor. Simple characteristics, low readout energy consumption (~fJ) owing to an absence of steady current, and fast readout operation (~ns) make ferroelectric source followers promising for voltage-sensing nonvolatile memory and voltage-sensing synapse as well as activation function (biased rectified linear unit) in computing-in-memory.

show abstract

“…Given the above limitations, the focus was on networks with a single hidden layer. There are many examples in the literature of implementing perceptrons, such as CMOS circuits [10,[43][44][45][46].…”

Section: Neural Networkmentioning

confidence: 99%

Study of the Complexity of CMOS Neural Network Implementations Featuring Heart Rate Detection

Baryczkowski,

Szczepaniak,

Matykiewicz

et al. 2023

Electronics

View full text Add to dashboard Cite

The growing popularity of edge computing goes hand in hand with the widespread use of systems based on artificial intelligence. There are many different technologies used to accelerate AI algorithms in end devices. One of the more efficient is CMOS technology thanks to the ability to control the physical parameters of the device. This article discusses the complexity of the semiconductor implementation of TinyML edge systems in relation to various criteria. In particular, the influence of the model parameters on the complexity of the system is analyzed. As a use case, a CMOS preprocessor device dedicated to detecting heart rate in wearable devices is used. The authors use the current and weak inversion operating modes, which allow the preprocessor to be powered by cells of the human energy harvesting class. This work analyzes the influence of tuning hyperparameters of the learning process on the performance of the final device. This article analyzes the relationships between the model parameters (accuracy and neural network size), input data parameters (sampling rates) and CMOS circuit parameters (circuit area, operating frequency and power consumption). Comparative analyses are performed using TSMC 65 nm CMOS technology. The results presented in this article may be useful to direct this work with the model in terms of the final implementation as the integrated circuit. The dependencies summarized in this work can also be used to initially estimate the costs of the hardware implementation of the model.

show abstract

Implementation of Analog Perceptron as an Essential Element of Configurable Neural Networks

Cited by 4 publications

References 47 publications

Neural Reduction of Image Data in Order to Determine the Quality of Malting Barley

Neural Reduction of Image Data in Order to Determine the Quality of Malting Barley

Ferroelectric source follower for voltage-sensing nonvolatile memory and computing-in-memory

Study of the Complexity of CMOS Neural Network Implementations Featuring Heart Rate Detection

Contact Info

Product

Resources

About