scholarly journals One-time learning in a biologically-inspired Salience-affected Artificial Neural Network (SANN)

2019 ◽  
Author(s):  
Leendert A Remmelzwaal ◽  
George F R Ellis ◽  
Jonathan Tapson
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Neural Dynamics ◽  
Proof Of Concept ◽  
Activation Functions ◽  
Learning Networks ◽  
Biologically Inspired ◽  
Artificial Neural ◽  
Validation Testing ◽  
And Robotics

AbstractIn this paper we introduce a novel Salience Affected Artificial Neural Network (SANN) that models the way neuromodulators such as dopamine and noradrenaline affect neural dynamics in the human brain by being distributed diffusely through neocortical regions. This allows one-time learning to take place through strengthening entire patterns of activation at one go. We present a model that accepts a salience signal, and returns a reverse salience signal. We demonstrate that we can tag an image with salience with only a single training iteration, and that the same image will then produces the highest reverse salience signal during classification. We explore the effects of salience on learning via its effect on the activation functions of each node, as well as on the strength of weights in the network. We demonstrate that a salience signal improves classification accuracy of the specific image that was tagged with salience, as well as all images in the same class, while penalizing images in other classes. Results are validated using 5-fold validation testing on MNIST and Fashion MNIST datasets. This research serves as a proof of concept, and could be the first step towards introducing salience tagging into Deep Learning Networks and robotics.

scholarly journals Predictive Modeling of a Leaf Conceptual Midpoint Quasi-Color (CMQ) Using an Artificial Neural Network

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 3938
Author(s):  
Ivan Simko
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Predictive Modeling ◽  
Leafy Vegetables ◽  
Proof Of Concept ◽  
Plant Leaves ◽  
Actual Color ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Very High

The color of plant leaves is moderated by the content of pigments, which can show considerable dorsiventral distribution. Two typical examples are leafy vegetables and ornamentals, wherein red and green color surfaces can be seen on the same leaf. The proof of concept is provided for predictive modeling of a leaf conceptual mid-point quasi-color (CMQ) from the content of pigments. The CMQ idea is based on the hypothesis that the content of pigments in leaves is associated with the combined color from both surfaces. The CMQ, which is calculated from CIELab color coordinates at adaxial and abaxial antipodes, is thus not an actual color, but a notion that can be used in modeling. The CMQ coordinates, predicted from the content of chlorophylls and anthocyanins by means of an artificial neural network (ANN), matched well with the CMQ coordinates empirically found on photosynthetically active leaves of lettuce (Lactuca sativa L.), but also with other plant species with comparable leaf attributes. Modeled values of lightness (qL*) decreased with the increasing content of both pigments, while the redness or greenness (qa*) and yellowness or blueness (qb*) of the CMQ were affected more by a relative content of chlorophylls and anthocyanins in leaves. The highest vividness of quasi-colors (qC*) was modeled for leaves with a high content of either pigment alone. The model predicted a substantially duller quasi-color for leaves with chlorophylls and anthocyanins present together, particularly when both pigments were present at very high levels.

scholarly journals An Artificial Neural Network Model to Predict the Thermal Properties of Concrete Using Different Neurons and Activation Functions

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Sehmus Fidan ◽  
Hasan Oktay ◽  
Suleyman Polat ◽  
Sarper Ozturk
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Thermal Properties ◽  
Thermal Property ◽  
Building Materials ◽  
Performance Indicator ◽  
Mechanical And Thermal Properties ◽  
Activation Functions ◽  
Marquardt Algorithm ◽  
Artificial Neural

Growing concerns on energy consumption of buildings by heating and cooling applications have led to a demand for improved insulating performances of building materials. The establishment of thermal property for a building structure is the key performance indicator for energy efficiency, whereas high accuracy and precision tests are required for its determination which increases time and experimental costs. The main scope of this study is to develop a model based on artificial neural network (ANN) in order to predict the thermal properties of concrete through its mechanical characteristics. Initially, different concrete samples were prepared, and their both mechanical and thermal properties were tested in accordance with ASTM and EN standards. Then, the Levenberg–Marquardt algorithm was used for training the neural network in the single hidden layer using 5, 10, 15, 20, and 25 neurons, respectively. For each thermal property, various activation functions such as tangent sigmoid functions and triangular basis functions were used to examine the best solution performance. Moreover, a cross-validation technique was used to ensure good generalization and to avoid overtraining. ANN results showed that the best overall R2 performances for the prediction of thermal conductivity, specific heat, and thermal diffusivity were obtained as 0.996, 0.983, and 0.995 for tansig activation functions with 25, 25, and 20 neurons, respectively. The performance results showed that there was a great consistency between the predicted and tested results, demonstrating the feasibility and practicability of the proposed ANN models for predicting the thermal property of a concrete.

scholarly journals An artificial Neural-Network Approach for Motor Hotspot Identification Based on Electroencephalography: A Proof-of-Concept Study

2021 ◽  
Author(s):  
Ga-Young Choi ◽  
Chang-Hee Han ◽  
Hyung-Tak Lee ◽  
Nam-Jong Paik ◽  
Won-Seok Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Motor Cortex ◽  
Transcranial Electrical Stimulation ◽  
Proof Of Concept ◽  
Mean Error ◽  
Eeg Data ◽  
Identification Approach ◽  
Artificial Neural ◽  
Error Distance

Background: To apply transcranial electrical stimulation (tES) to the motor cortex, motor hotspots are generally identified using motor evoked potentials by transcranial magnetic stimulation (TMS). The objective of this study is to validate the feasibility of a novel electroencephalography (EEG)-based motor-hotspot-identification approach using a machine learning technique as a potential alternative to TMS. Methods: EEG data were measured using 63 channels from thirty subjects as they performed a simple finger tapping task. Power spectral densities of the EEG data were extracted from six frequency bands (delta, theta, alpha, beta, gamma, and full) and were independently used to train and test an artificial neural network for motor hotspot identification. The 3D coordinate information of individual motor hotspots identified by TMS were quantitatively compared with those estimated by our EEG-based motor-hotspot-identification approach to assess its feasibility. Results: The minimum mean error distance between the motor hotspot locations identified by TMS and our proposed motor-hotspot-identification approach was 0.22 & 0.03 cm, demonstrating the proof-of-concept of our proposed EEG-based approach. A mean error distance of 1.32 & 0.15 cm was measured when using only nine channels attached to the middle of the motor cortex, showing the possibility of practically using the proposed motor-hotspot-identification approach based on a relatively small number of EEG channels. Conclusion: We demonstrated the feasibility of our novel EEG-based motor-hotspot-identification method. It is expected that our approach can be used as an alternative to TMS for motor hotspot identification. In particular, its usability would significantly increase when using a recently developed portable tES device integrated with an EEG device.

scholarly journals Advanced Stochastic Optimization Algorithm for Deep Learning Artificial Neural Networks in Banking and Finance Industries

2019 ◽  
Vol 1 (1) ◽  
pp. p8
Author(s):  
Jamilu Auwalu Adamu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Deep Learning ◽  
Probability Distribution ◽  
Trial And Error ◽  
Activation Functions ◽  
Data Set ◽  
Artificial Neural

One of the objectives of this paper is to incorporate fat-tail effects into, for instance, Sigmoid in order to introduce Transparency and Stability into the existing stochastic Activation Functions. Secondly, according to the available literature reviewed, the existing set of Activation Functions were introduced into the Deep learning Artificial Neural Network through the “Window” not properly through the “Legitimate Door” since they are “Trial and Error “and “Arbitrary Assumptions”, thus, the Author proposed a “Scientific Facts”, “Definite Rules: Jameel’s Stochastic ANNAF Criterion”, and a “Lemma” to substitute not necessarily replace the existing set of stochastic Activation Functions, for instance, the Sigmoid among others. This research is expected to open the “Black-Box” of Deep Learning Artificial Neural networks. The author proposed a new set of advanced optimized fat-tailed Stochastic Activation Functions EMANATED from the AI-ML-Purified Stocks Data  namely; the Log – Logistic (3P) Probability Distribution (1st), Cauchy Probability Distribution (2nd), Pearson 5 (3P) Probability Distribution (3rd), Burr (4P) Probability Distribution (4th), Fatigue Life (3P) Probability Distribution (5th), Inv. Gaussian (3P) Probability Distribution (6th), Dagum (4P) Probability Distribution (7th), and Lognormal (3P) Probability Distribution (8th) for the successful conduct of both Forward and Backward Propagations of Deep Learning Artificial Neural Network. However, this paper did not check the Monotone Differentiability of the proposed distributions. Appendix A, B, and C presented and tested the performances of the stressed Sigmoid and the Optimized Activation Functions using Stocks Data (2014-1991) of Microsoft Corporation (MSFT), Exxon Mobil (XOM), Chevron Corporation (CVX), Honda Motor Corporation (HMC), General Electric (GE), and U.S. Fundamental Macroeconomic Parameters, the results were found fascinating. Thus, guarantee, the first three distributions are excellent Activation Functions to successfully conduct any Stock Deep Learning Artificial Neural Network. Distributions Number 4 to 8 are also good Advanced Optimized Activation Functions. Generally, this research revealed that the Advanced Optimized Activation Functions satisfied Jameel’s ANNAF Stochastic Criterion depends on the Referenced Purified AI Data Set, Time Change and Area of Application which is against the existing “Trial and Error “and “Arbitrary Assumptions” of Sigmoid, Tanh, Softmax, ReLu, and Leaky ReLu.

Definition of Artificial Neural Network

2018 ◽  
pp. 32-46
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Learning Tools ◽  
Activation Functions ◽  
Mathematical Definition ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Definition Of

This chapter is an explanation of artificial neural network (ANN), which is one of the machine learning tools applied for medical purposes. The biological and mathematical definition of neural network is provided and the activation functions effective for processing are listed. Some figures are collected for better understanding.

scholarly journals An artificial neural-network approach to identify motor hotspot for upper-limb based on electroencephalography: a proof-of-concept study

2021 ◽  
Vol 18 (1) ◽  
Author(s):  
Ga-Young Choi ◽  
Chang-Hee Han ◽  
Hyung-Tak Lee ◽  
Nam-Jong Paik ◽  
Won-Seok Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Motor Cortex ◽  
Transcranial Electrical Stimulation ◽  
Proof Of Concept ◽  
Mean Error ◽  
Eeg Data ◽  
Identification Approach ◽  
Artificial Neural ◽  
Error Distance

Abstract Background To apply transcranial electrical stimulation (tES) to the motor cortex, motor hotspots are generally identified using motor evoked potentials by transcranial magnetic stimulation (TMS). The objective of this study is to validate the feasibility of a novel electroencephalography (EEG)-based motor-hotspot-identification approach using a machine learning technique as a potential alternative to TMS. Methods EEG data were measured using 63 channels from thirty subjects as they performed a simple finger tapping task. Power spectral densities of the EEG data were extracted from six frequency bands (delta, theta, alpha, beta, gamma, and full) and were independently used to train and test an artificial neural network for motor hotspot identification. The 3D coordinate information of individual motor hotspots identified by TMS were quantitatively compared with those estimated by our EEG-based motor-hotspot-identification approach to assess its feasibility. Results The minimum mean error distance between the motor hotspot locations identified by TMS and our proposed motor-hotspot-identification approach was 0.22 ± 0.03 cm, demonstrating the proof-of-concept of our proposed EEG-based approach. A mean error distance of 1.32 ± 0.15 cm was measured when using only nine channels attached to the middle of the motor cortex, showing the possibility of practically using the proposed motor-hotspot-identification approach based on a relatively small number of EEG channels. Conclusion We demonstrated the feasibility of our novel EEG-based motor-hotspot-identification method. It is expected that our approach can be used as an alternative to TMS for motor hotspot identification. In particular, its usability would significantly increase when using a recently developed portable tES device integrated with an EEG device.

Sign in / Sign up

Export Citation Format

Share Document