scholarly journals Back-propagation learning in deep Spike-By-Spike networks

2019 ◽  
Author(s):  
David Rotermund ◽  
Klaus R. Pawelzik
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Action Potentials ◽  
Back Propagation ◽  
Learning Rule ◽  
Building Blocks ◽  
Classification Performance ◽  
Generative Models ◽  
Learning Method ◽  
Discrete Action

ABSTRACTNeural networks are important building blocks in technical applications. These artificial neural networks (ANNs) rely on noiseless continuous signals in stark contrast to the discrete action potentials stochastically exchanged among the neurons in real brains. A promising approach towards bridging this gap are the Spike-by-Spike (SbS) networks which represent a compromise between non-spiking and spiking versions of generative models that perform inference on their inputs. What is still missing are algorithms for finding weight sets that would optimize the output performances of deep SbS networks with many layers.Here, a learning rule for hierarchically organized SbS networks is derived. The properties of this approach are investigated and its functionality demonstrated by simulations. In particular, a Deep Convolutional SbS network for classifying handwritten digits (MNIST) is presented. When applied together with an optimizer this learning method achieves a classification performance of roughly 99.3% on the MNIST test data. Thereby it approaches the benchmark results of ANNs without extensive parameter optimization. We envision that with this learning rule SBS networks will provide a new basis for research in neuroscience and for technical applications, especially when they become implemented on specialized computational hardware.

A NEW TECHNIQUE TO PREDICT THE FRACTURES DIP USING ARTIFICIAL NEURAL NETWORKS AND IMAGE LOGS DATA

2015 ◽  
Vol 75 (11) ◽  
Author(s):  
Mostafa Alizadeh ◽  
Zohreh Movahed ◽  
Radzuan Junin ◽  
Rahmat Mohsin ◽  
Mehdi Alizadeh ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Oil And Gas ◽  
Back Propagation ◽  
Learning Rule ◽  
The Other ◽  
New Technique ◽  
Ann Model ◽  
Artificial Neural ◽  
A New Technique

Fractures provide the place for oil and gas to be reserved and they also can provide the pathway for them to move into the well, so having a proper knowledge of them is essential and every year the companies try to improve the existed softwares in this technology. In this work, the new technique is introduced to be added as a new application to the existed softwares such as Petrel and geoframe softwares. The data used in this work are image logs and the other geological logs data of tree wells located in Gachsaran field, wells number GS-A, GS-B and GS-C. The new technique by using the feed-forward artificial neural networks (ANN) with back-propagation learning rule can predict the fracture dip data of the third well using the data from the other 2 wells. The result obtained showed that the ANN model can simulate the relationship between fractures dips in these 3 wells which the multiple R of training and test sets for the ANN model is 0.95099 and 0.912197, respectively.

scholarly journals A STUDY ON A BIONIC PATTERN CLASSIFIER BASED ON OLFACTORY NEURAL SYSTEM

2006 ◽  
Vol 16 (08) ◽  
pp. 2425-2434 ◽  
Author(s):  
XU LI ◽  
GUANG LI ◽  
LE WANG ◽  
WALTER J. FREEMAN
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Action Potentials ◽  
Neural System ◽  
Classification Performance ◽  
High Dimensional ◽  
Chaotic Attractors ◽  
Noise Levels ◽  
Chaotic Neural Network

This paper presents a simulation of a biological olfactory neural system with a KIII set, which is a high-dimensional chaotic neural network. The KIII set differs from conventional artificial neural networks by use of chaotic attractors for memory locations that are accessed by, chaotic trajectories. It was designed to simulate the patterns of action potentials and EEG waveforms observed in electrophysiological experiments, and has proved its utility as a model for biological intelligence in pattern classification. An application to recognition of handwritten numerals is presented here, in which the classification performance of the KIII network under different noise levels was investigated.

Prediction of Ferrite-Martensite Dual-Phase Steels Mechanical Properties by Use of Artificial Neural Networks

2013 ◽  
Vol 773-774 ◽  
pp. 268-274
Author(s):  
Amir Ghiami ◽  
Ramin Khamedi
Keyword(s):  
Mechanical Properties ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Back Propagation ◽  
Total Elongation ◽  
Ultimate Tensile Stress ◽  
Dual Phase ◽  
Dual Phase Steels ◽  
Good Ability ◽  
Artificial Neural

This paper presents an investigation of the capabilities of artificial neural networks (ANN) in predicting some mechanical properties of Ferrite-Martensite dual-phase steels applicable for different industries like auto-making. Using ANNs instead of different destructive and non-destructive tests to determine the material properties, reduces costs and reduces the need for special testing facilities. Networks were trained with use of a back propagation (BP) error algorithm. In order to provide data for training the ANNs, mechanical properties, inter-critical annealing temperature and information about the microstructures of many specimens were examined. After the ANNs were trained, the four parameters of yield stress, ultimate tensile stress, total elongation and the work hardening exponent were simulated. Finally a comparison of the predicted and experimental values indicates that the results obtained from the given input data reveal a good ability of the well-trained ANN to predict the described mechanical properties.

Rainfall Prediction by Artificial Neural Networks Trained using Different Climate Variables

2021 ◽  
Author(s):  
Mateus Alexandre da Silva ◽  
Marina Neves Merlo ◽  
Michael Silveira Thebaldi ◽  
Danton Diego Ferreira ◽  
Felipe Schwerz ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Input Data ◽  
Back Propagation ◽  
Metropolitan Region ◽  
Climate Variables ◽  
Back Propagation Algorithm ◽  
Rainfall Prediction ◽  
Artificial Neural ◽  
Belo Horizonte

Abstract Predicting rainfall can prevent and mitigate damages caused by its deficit or excess, besides providing necessary tools for adequate planning for the use of water. This research aimed to predict the monthly rainfall, one month in advance, in four municipalities in the metropolitan region of Belo Horizonte, using artificial neural networks (ANN) trained with different climate variables, and to indicate the suitability of such variables as inputs to these models. The models were developed through the MATLAB® software version R2011a, using the NNTOOL toolbox. The ANN’s were trained by the multilayer perceptron architecture and the Feedforward and Back propagation algorithm, using two combinations of input data were used, with 2 and 6 variables, and one combination of input data with 3 of the 6 variables most correlated to observed rainfall from 1970 to 1999, to predict the rainfall from 2000 to 2009. The most correlated variables to the rainfall of the following month are the sequential number corresponding to the month, total rainfall and average compensated temperature, and the best performance was obtained with these variables. Furthermore, it was concluded that the performance of the models was satisfactory; however, they presented limitations for predicting months with high rainfall.

Artificial neural networks back propagation algorithm for cutting force components predictions

2013 ◽  
Vol 14 (6) ◽  
pp. 431-439 ◽  
Author(s):  
Issam Hanafi ◽  
Francisco Mata Cabrera ◽  
Abdellatif Khamlichi ◽  
Ignacio Garrido ◽  
José Tejero Manzanares
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Cutting Force ◽  
Back Propagation ◽  
Back Propagation Algorithm ◽  
Propagation Algorithm ◽  
Cutting Force Components ◽  
Artificial Neural ◽  
Force Components

Combining BP with PSO algorithms in weights optimisation and ANNs training for mass appraisal of properties

2018 ◽  
Vol 11 (2) ◽  
pp. 290-314 ◽  
Author(s):  
Joseph Awoamim Yacim ◽  
Douw Gert Brand Boshoff
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Predictive Accuracy ◽  
Back Propagation ◽  
Particle Swarm ◽  
Particle Swarm Optimisation ◽  
Content Type ◽  
Attribute Weights ◽  
Artificial Neural ◽  
And Training

Purpose The paper aims to investigate the application of particle swarm optimisation and back propagation in weights optimisation and training of artificial neural networks within the mass appraisal industry and to compare the performance with standalone back propagation, genetic algorithm with back propagation and regression models. Design/methodology/approach The study utilised linear regression modelling before the semi-log and log-log models with a sample of 3,242 single-family dwellings. This was followed by the hybrid systems in the selection of optimal attribute weights and training of the artificial neural networks. Also, the standalone back propagation algorithm was used for the network training, and finally, the performance of each model was evaluated using accuracy test statistics. Findings The study found that combining particle swarm optimisation with back propagation in global and local search for attribute weights enhances the predictive accuracy of artificial neural networks. This also enhances transparency of the process, because it shows relative importance of attributes. Research limitations/implications A robust assessment of the models’ predictive accuracy was inhibited by fewer accuracy test statistics found in the software. The research demonstrates the efficacy of combining two models in the assessment of property values. Originality/value This work demonstrated the practicability of combining particle swarm optimisation with back propagation algorithms in finding optimal weights and training of the artificial neural networks within the mass appraisal environment.

Applying Neural Networks for Modeling of Financial Assets

2018 ◽  
pp. 172-204
Author(s):  
Dmitry Averchenko ◽  
Artem Aldyrev
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Standard Deviation ◽  
Learning Process ◽  
Moving Average ◽  
Back Propagation ◽  
Financial Assets ◽  
Movement Index ◽  
Analytical System ◽  
Feedback Neural Networks

The purpose of this chapter is to develop an analytical system for forecasting prices of financial assets with the use of artificial neural networks technology. Proposed by the authors, the analytical system consists of several neural networks, each of which makes the forecast of financial assets prices. The system includes recurrence (with feedback) neural networks with sigmoidal activation formula. This allows the networks to “remember” a sequence of reactions to the same stimulus. The learning process of neural networks is performed using an algorithm of back propagation of error. The key parameters of forecast for this analytical system are the indicators presented by the terminal MetaTrader 4-broker Forex Club: Average Directional и Movement Index; Bollinger Bands; Envelopes; Ichimoku Kinko Hyo; Moving Average; Parabolic SAR; Standard Deviation; Average True Range; and others.

Sign in / Sign up

Export Citation Format

Share Document