A Hardware-Efficient Sigmoid Function With Adjustable Precision for a Neural Network System

Tsai, Chang-Hung; Chih, Yu-Ting; Wong, Wing Hung; Lee, Chen‐Yi

doi:10.1109/tcsii.2015.2456531

Cited by 63 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we have deliberately restricted ourselves to systems that split the input space via clear-cut binary decisions. Naturally, a new degree of freedom is unlocked if we move away from the simple McCulloch-Pitts-like step activation function and into different functions such as ReLU [18], sigmoids [19] etc. However, this would require the development of (ideally very simple) read-out structures that modularly attach to the output of the circuits shown in Figs.…”

Section: Resultsmentioning

confidence: 99%

Processing big-data with Memristive Technologies: Splitting the Hyperplane Efficiently

Serb

Papandroulidakis

Khiat

et al. 2018

2018 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

An important cornerstone of data processing is the ability to efficiently capture structure in data. This entails treating the input space as a hyperplane that needs partitioning. We argue that several modern electronic systems can be understood as carrying out such partitionings: from standard logic gates to Artificial Neural Networks (ANNs). More recently, memristive technologies equipped such systems with the benefit of continuous tunability directly in hardware, thus rendering these reconfigurable in a power and space efficient manner. Here, we demonstrate several proof-of-concept examples where memristors enable circuits optimised to carry out different flavours of the fundamental task of splitting the hyperplane. These include threshold logic and receptive field based classifiers that are presented within the context of a unified perspective.

show abstract

Section: Resultsmentioning

confidence: 99%

Processing big-data with Memristive Technologies: Splitting the Hyperplane Efficiently

Serb

Papandroulidakis

Khiat

et al. 2018

2018 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

show abstract

“…One of the functions that has an S-shaped curve is known as sigmoid function. It is widely used in artificial neural network to introduce the nonlinearity model [6][7][8] and backpropagation learning [9]. It has also been used to predict and make some decision making on how much money can be saved based on the amount available in the current account balance [10].…”

Section: S-shaped Curve As a Tool For Predictionmentioning

confidence: 99%

A Novel S-Regression Model on an Auto Price

Salim¹,

Abu²

2018

IJET

View full text Add to dashboard Cite

A simple linear regression model is useful in a prediction model. A general linear regression beyond a single independent variable is still not popular. A nonlinear regression can be easily produced a better predictive model but it is difficult to construct. The objective of this paper is to propose a technique for predicting the price of used cars in Malaysia using S-shaped curve model. In this paper, the S-shaped Membership Function [SMF] is used as the basis to develop a novel S-Regression model. Comparisons between linear regression, cubic regression and S-Regression have been made on the used car prices. The mean squared error of S-Regression model is found to be closer to cubic regression than the linear regression. S-Regression model is found to be quite suitable to represent the relationship between the price of a used car and the make year of a car. The result demonstrates that the S-Regression model gives better and practical estimate of the price of a used car in Malaysia.

show abstract

“…In this paper, the neural network uses back propagation algorithm, also known as BP algorithm [1] [2].…”

Section: Overview Of Bp Neural Networkmentioning

confidence: 99%

Drink-driving Behavior Research Based on Artificial Neural Network

Shang¹,

Zhang²

2018

Proceedings of the 2018 Joint International Advanced Engineering and Technology Research Conference (JIAET 2018)

View full text Add to dashboard Cite

Abstract. Drink-driving, alone traffic police department regulation is not enough. Only taking the necessary scientific and technological means, drink-driving illegal behavior can be effectively controlled. In this paper, first, we established the detection of drink-driving behavior model of BP neural network; Then use the sensor array, collecting the cab and the driver's own state parameters; Next normalize samples from the samples library, which are used to training network; Finally acts of drink-driving simulation test ,which can get the driver's extent of drinking and the result of driving behavior. So you can control the driving behavior according to drivers extent of drinking and the result of driving behavior.

show abstract

A Hardware-Efficient Sigmoid Function With Adjustable Precision for a Neural Network System

Cited by 63 publications

References 16 publications

Processing big-data with Memristive Technologies: Splitting the Hyperplane Efficiently

Processing big-data with Memristive Technologies: Splitting the Hyperplane Efficiently

A Novel S-Regression Model on an Auto Price

Drink-driving Behavior Research Based on Artificial Neural Network

Contact Info

Product

Resources

About