Low-error approximation of artificial neuron sigmoid function and its derivative

2009 ◽  
Vol 45 (21) ◽  
pp. 1082 ◽  
Author(s):  
A. Armato ◽  
L. Fanucci ◽  
G. Pioggia ◽  
D. De Rossi
Keyword(s):  
Sigmoid Function ◽  
Artificial Neuron

scholarly journals Theory of a superconducting artificial neuron for extended backpropagation learning algorism

2018 ◽  
Vol 7 (3.29) ◽  
pp. 170
Author(s):  
Haruna Katayama ◽  
Toshiyuki Fujii ◽  
Noriyuki Hatakenaka
Keyword(s):  
Magnetic Fields ◽  
Josephson Junctions ◽  
Superconducting Devices ◽  
Sigmoid Function ◽  
Fixed Temperature ◽  
Artificial Neuron ◽  
Backpropagation Learning

An artificial neuron using superconducting devices, so-called double SQUID, applicable to the extended backpropagation learning algorism is studied. It is shown that the tunable slope of the sigmoid function required in the algorism can be achieved under the fixed temperature by externally applied magnetic fields threading the ring with two Josephson junctions in the double SQUID.  

scholarly journals Theory of a quantum artificial neuron based on superconducting devices

2018 ◽  
Vol 7 (3.29) ◽  
pp. 150
Author(s):  
Haruna Katayama ◽  
Toshiyuki Fujii ◽  
Noriyuki Hatakenaka
Keyword(s):  
Superconducting Devices ◽  
Quantum Mechanical ◽  
Sigmoid Function ◽  
Artificial Neuron ◽  
Rf Squid ◽  
Double Well Potential ◽  
Flux Qubit ◽  
Coherent Quantum

An artificial neuron using superconducting devices, so-called rf SQUID, working at the quantum-mechanical domain is studied. It is shown that quantum rf SQUID regarded as flux qubit can act as an artificial neuron with sigmoid function generated by coherent quantum-mechanical transitions between wells in double well potential representing rf SQUID.   

S-CCCapsule: Pneumonia detection in chest X-ray images using skip-connected convolutions and capsule neural network

2021 ◽  
pp. 1-25
Author(s):  
Kwabena Adu ◽  
Yongbin Yu ◽  
Jingye Cai ◽  
Victor Dela Tattrah ◽  
James Adu Ansere ◽  
...  
Keyword(s):  
Neural Network ◽  
Human Error ◽  
Medical Center ◽  
Confusion Matrix ◽  
Area Under The Curve ◽  
Dynamic Routing ◽  
Sigmoid Function ◽  
Radiological Society ◽  
Chest X Ray ◽  
Sensitivity Specificity

The squash function in capsule networks (CapsNets) dynamic routing is less capable of performing discrimination of non-informative capsules which leads to abnormal activation value distribution of capsules. In this paper, we propose vertical squash (VSquash) to improve the original squash by preventing the activation values of capsules in the primary capsule layer to shrink non-informative capsules, promote discriminative capsules and avoid high information sensitivity. Furthermore, a new neural network, (i) skip-connected convolutional capsule (S-CCCapsule), (ii) Integrated skip-connected convolutional capsules (ISCC) and (iii) Ensemble skip-connected convolutional capsules (ESCC) based on CapsNets are presented where the VSquash is applied in the dynamic routing. In order to achieve uniform distribution of coupling coefficient of probabilities between capsules, we use the Sigmoid function rather than Softmax function. Experiments on Guangzhou Women and Children’s Medical Center (GWCMC), Radiological Society of North America (RSNA) and Mendeley CXR Pneumonia datasets were performed to validate the effectiveness of our proposed methods. We found that our proposed methods produce better accuracy compared to other methods based on model evaluation metrics such as confusion matrix, sensitivity, specificity and Area under the curve (AUC). Our method for pneumonia detection performs better than practicing radiologists. It minimizes human error and reduces diagnosis time.

scholarly journals Blind Deblurring Based on Sigmoid Function

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3484
Author(s):  
Shuhan Sun ◽  
Lizhen Duan ◽  
Zhiyong Xu ◽  
Jianlin Zhang
Keyword(s):  
Performance Optimization ◽  
Degradation Process ◽  
Image Deconvolution ◽  
Sigmoid Function ◽  
Blind Image Deblurring ◽  
Linear Estimators ◽  
Blind Deblurring ◽  
Degraded Image ◽  
Excellent Property ◽  
Blind Image

Blind image deblurring, also known as blind image deconvolution, is a long-standing challenge in the field of image processing and low-level vision. To restore a clear version of a severely degraded image, this paper proposes a blind deblurring algorithm based on the sigmoid function, which constructs novel blind deblurring estimators for both the original image and the degradation process by exploring the excellent property of sigmoid function and considering image derivative constraints. Owing to these symmetric and non-linear estimators of low computation complexity, high-quality images can be obtained by the algorithm. The algorithm is also extended to image sequences. The sigmoid function enables the proposed algorithm to achieve state-of-the-art performance in various scenarios, including natural, text, face, and low-illumination images. Furthermore, the method can be extended naturally to non-uniform deblurring. Quantitative and qualitative experimental evaluations indicate that the algorithm can remove the blur effect and improve the image quality of actual and simulated images. Finally, the use of sigmoid function provides a new approach to algorithm performance optimization in the field of image restoration.

A new reaching law for sliding mode observer of controllable excitation linear synchronous motor

2021 ◽  
pp. 014233122110320
Author(s):  
Xiaolei Shi ◽  
Yipeng Lan ◽  
Yunpeng Sun ◽  
Cheng Lei
Keyword(s):  
Sliding Mode ◽  
Dynamic Performance ◽  
Angular Position ◽  
Lyapunov Stability Theory ◽  
Synchronous Motor ◽  
Position Estimation ◽  
Sliding Mode Observer ◽  
Sigmoid Function ◽  
Reaching Law ◽  
Linear Synchronous Motor

This paper presents a sliding mode observer (SMO) with new reaching law (NRL) for observing the real-time linear speed of a controllable excitation linear synchronous motor (CELSM). For the purpose of balancing the dilemma between the rapidity requirement of dynamic performance and the chattering reduction on sliding mode surface, the proposed SMO with NRL optimizes the reaching way of the conventional constant rate reaching law (CRRL) to the sliding mode surface by connecting the reaching process with system states and the sliding mode surface. The NRL is based on sigmoid function and power function, with proper options of exponential term and power term, the NRL is capable of eliminating the effect of chattering on accuracy of the angular position estimation and speed estimation. Compared with conventional CRRL, the SMO with NRL achieves suppressing the chattering phenomenon and tracking the transient process rapidly and accurately. The stability analysis is given to prove the convergence of the SMO through the Lyapunov stability theory. Simulation and experimental results show the effectiveness of the proposed NRL method.

scholarly journals In Situ Shear Test for Revealing the Mechanical Properties of the Gravelly Slip Zone Soil

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6531 ◽  
Author(s):  
Zongxing Zou ◽  
Qi Zhang ◽  
Chengren Xiong ◽  
Huiming Tang ◽  
Lei Fan ◽  
...  
Keyword(s):  
Mechanical Property ◽  
Plastic Deformation ◽  
Shear Test ◽  
Slip Zone ◽  
Three Gorges Reservoir Area ◽  
Silty Clay ◽  
Sigmoid Function ◽  
In Situ Test ◽  
Deformation Stage

Slip zone soil is usually composed of clay or silty clay; in some special geological environments, it contains gravels, which make the properties of the slip zone soil more complex. Unfortunately, in many indoor shear tests, gravels are removed to meet the demands of apparatus size, and the in situ mechanical property of the gravelly slip zone soil is rarely studied. In this study, the shear mechanical property of the gravelly slip zone soil of Huangtupo landslide in the Three Gorges Reservoir area of China was investigated by the in situ shear test. The test results show that the shear deformation process of the gravelly slip zone soil includes an elastic deformation stage, elastic–plastic deformation stage, and plastic deformation stage. Four functions were introduced to express the shear constitutive model of the gravelly slip zone soil, and the asymmetric sigmoid function was demonstrated to be the optimum one to describe the relationship of the shear stress and shear displacement with a correlation coefficient of 0.986. The comparison between the in situ test and indoor direct shear test indicates that gravels increase the strength of the slip zone soil. Therefore, the shear strength parameters of the gravelly slip zone soil obtained by the in situ test are more preferable for evaluating the stability of the landslide and designing the anti-slide structures.

The Modelling of Hysteresis in Magnetorheological Dampers Using a Generalised Prandtl-Ishlinskii Approach

2010 ◽  
Author(s):  
Kun Wang ◽  
Ying Zhang ◽  
Richard W. Jones
Keyword(s):  
Mr Damper ◽  
Control Analysis ◽  
Sigmoid Function ◽  
Magnetorheological Dampers ◽  
Operating Characteristics ◽  
Major Drawback ◽  
Analysis And Design ◽  
Force Velocity ◽  
Play Operator ◽  
Fidelity Model

The major drawback of magnetorheological dampers (MR) lies in their non-linear and hysteretic force-velocity response. To take full advantage of the operating characteristics of these devices a high fidelity model is required for control analysis and design. In this contribution the ability of a generalised PI operator-based model to represent the characteristics of a commercially available MR damper is examined. This approach allows the user to define the PI operator to best match the hysteresis characteristics. For the MR damper the force-velcoity hysteresis characteristic is ‘S’ shaped and constrained. Two possibilities will be examined here for the generalised play operator; an hyperbolic tan function and a symmetric sigmoid function.

scholarly journals Emulation with Organic Memristive Devices of Impairment of LTP Mechanism in Neurodegenerative Disease Pathology

2017 ◽  
Vol 2017 ◽  
pp. 1-8 ◽  
Author(s):  
Silvia Battistoni ◽  
Victor Erokhin ◽  
Salvatore Iannotta
Keyword(s):  
Neural Network ◽  
Information Transmission ◽  
Common Sense ◽  
Artificial Neuron ◽  
Cell Network ◽  
Neuron Networks ◽  
A Cell ◽  
The Common ◽  
Major Progress ◽  
Single Synapse

We explore and demonstrate the extension of the synapse-mimicking properties of memristive devices to a dysfunctional synapse as it occurs in the Alzheimer’s disease (AD) pathology. The ability of memristive devices to reproduce synapse properties such as LTP, LTD, and STDP has been already widely demonstrated, and moreover, they were used for developing artificial neuron networks (perceptrons) able to simulate the information transmission in a cell network. However, a major progress would be to extend the common sense of neuromorphic device even to the case of dysfunction of natural synapses. Can memristors efficiently simulate them? We provide here evidences of the ability of emulating the dysfunctional synaptic behavior typical of the AD pathology with organic memristive devices considering the effect of the disease not only on a single synapse but also in the case of a neural network, composed by numerous synapses.

Sign in / Sign up

Export Citation Format

Share Document