Evaluation of Parameter Contribution to Neural Network Size and Fitness in ATHENA for Genetic Analysis

2014 ◽  
pp. 211-224
Author(s):  
Ruowang Li ◽  
Emily R. Holzinger ◽  
Scott M. Dudek ◽  
Marylyn D. Ritchie
Keyword(s):  
Neural Network ◽  
Genetic Analysis ◽  
Network Size

Pattern Storage, Bifurcations, and Groupwise Correlation Structure of an Exactly Solvable Asymmetric Neural Network Model

2018 ◽  
Vol 30 (5) ◽  
pp. 1258-1295 ◽  
Author(s):  
Diego Fasoli ◽  
Anna Cattani ◽  
Stefano Panzeri
Keyword(s):  
Neural Network ◽  
Evolution Equations ◽  
Learning Rule ◽  
Network Size ◽  
Oscillatory Behavior ◽  
Spin Model ◽  
Membrane Potentials ◽  
Neural Network Models ◽  
Conditional Probability Distribution ◽  
Firing Rates

Despite their biological plausibility, neural network models with asymmetric weights are rarely solved analytically, and closed-form solutions are available only in some limiting cases or in some mean-field approximations. We found exact analytical solutions of an asymmetric spin model of neural networks with arbitrary size without resorting to any approximation, and we comprehensively studied its dynamical and statistical properties. The network had discrete time evolution equations and binary firing rates, and it could be driven by noise with any distribution. We found analytical expressions of the conditional and stationary joint probability distributions of the membrane potentials and the firing rates. By manipulating the conditional probability distribution of the firing rates, we extend to stochastic networks the associating learning rule previously introduced by Personnaz and coworkers. The new learning rule allowed the safe storage, under the presence of noise, of point and cyclic attractors, with useful implications for content-addressable memories. Furthermore, we studied the bifurcation structure of the network dynamics in the zero-noise limit. We analytically derived examples of the codimension 1 and codimension 2 bifurcation diagrams of the network, which describe how the neuronal dynamics changes with the external stimuli. This showed that the network may undergo transitions among multistable regimes, oscillatory behavior elicited by asymmetric synaptic connections, and various forms of spontaneous symmetry breaking. We also calculated analytically groupwise correlations of neural activity in the network in the stationary regime. This revealed neuronal regimes where, statistically, the membrane potentials and the firing rates are either synchronous or asynchronous. Our results are valid for networks with any number of neurons, although our equations can be realistically solved only for small networks. For completeness, we also derived the network equations in the thermodynamic limit of infinite network size and we analytically studied their local bifurcations. All the analytical results were extensively validated by numerical simulations.

Prediction of slip in cable-drum systems using structured neural networks

2013 ◽  
Vol 228 (3) ◽  
pp. 441-456 ◽  
Author(s):  
Ergin Kilic ◽  
Melik Dolen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Size ◽  
Network Architectures ◽  
Network Development ◽  
Low Velocity ◽  
Error Band ◽  
Artificial Neural ◽  
Recurrent Type ◽  
Selection Of

This study focuses on the slip prediction in a cable-drum system using artificial neural networks for the prospect of developing linear motion sensing scheme for such mechanisms. Both feed-forward and recurrent-type artificial neural network architectures are considered to capture the slip dynamics of cable-drum mechanisms. In the article, the network development is presented in a progressive (step-by-step) fashion for the purpose of not only making the design process transparent to the readers but also highlighting the corresponding challenges associated with the design phase (i.e. selection of architecture, network size, training process parameters, etc.). Prediction performances of the devised networks are evaluated rigorously via an experimental study. Finally, a structured neural network, which embodies the network with the best prediction performance, is further developed to overcome the drift observed at low velocity. The study illustrates that the resulting structured neural network could predict the slip in the mechanism within an error band of 100 µm when an absolute reference is utilized.

An Efficient Neural Network Model for Path Planning of Car-like Robots in Dynamic Environment

2000 ◽  
Vol 4 (3) ◽  
pp. 220-229 ◽  
Author(s):  
Simon X. Yang ◽  
◽  
Max Meng ◽  
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Real Time ◽  
Dynamic Environment ◽  
Lyapunov Stability Theory ◽  
Network Size ◽  
Computationally Efficient ◽  
Neural Network Approach ◽  
The Neural Network ◽  
The Stability

In this paper, an effcient neural network approach to real-time path planning with obstacle avoidance of holonomic car-like robots in a dynamic environment is proposed. The dynamics of each neuron in this biologically inspired, topologically organized neural network is characterized by a shunting equation or an additive equation. The state space of the neural network is the configuration space of the robot. There are only local lateral connections among neurons. Thus the computational complexity linearly depends on the neural network size. The real-time collision-free path is planned through the dynamic neural activity landscape of the neural network without explicitly searching over neither the free workspace nor the collision paths, without any prior knowledge of the dynamic environment, without any learning procedures, and without any local collision checking procedures at each step of the robot movement. Therefore it is computationally efficient. The stability of the neural network is proven by both qualitative analysis and the Lyapunov stability theory. The effectiveness and efficiency are demonstrated through simulation studies.

scholarly journals The Evaluation of Deep Neural Networks and X-Ray as a Practical Alternative for Diagnosis and Management of COVID-19

2020 ◽  
Author(s):  
Mohamed Elgendi ◽  
Rich Fletcher ◽  
Newton Howard ◽  
Carlo Menon ◽  
Rabab Ward
Keyword(s):  
Neural Network ◽  
New Technology ◽  
Network Size ◽  
Front Line ◽  
High Resolution Computed Tomography ◽  
Training Time ◽  
X Ray ◽  
Diagnosis And Management ◽  
Diagnostic Technology ◽  
Time Accuracy

High-resolution computed tomography radiology is a critical tool in the diagnosis and management of COVID-19 infection; however, in smaller clinics around the world, there is a shortage of radiologists available to analyze these images. In this paper, we compare the performance of 16 available deep learning algorithms to help identify COVID19. We utilize an already existing diagnostic technology (X-ray) and an already existing neural network (ResNet-50) to diagnose COVID-19. Our approach eliminates the extra time and resources needed to develop new technology and associated algorithm, thus aiding the front-line in the race against the COVID-19 pandemic. Results show that ResNet-50 is the optimal pretrained neural network for the detection of COVID-19, using three different cross-validation ratios, based on training time, accuracy, and network size. We also present a custom visualization of the results that can be used to highlight important visual biomarkers of the disease and disease progression.

scholarly journals Antifragility Predicts the Robustness and Evolvability of Biological Networks through Multi-Class Classification with a Convolutional Neural Network

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 986
Author(s):  
Hyobin Kim ◽  
Stalin Muñoz ◽  
Pamela Osuna ◽  
Carlos Gershenson
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Biological Networks ◽  
Computational Cost ◽  
Network Models ◽  
Network Size ◽  
Essential Properties ◽  
Before And After ◽  
Multi Class Classification ◽  
High Computational Cost

Robustness and evolvability are essential properties to the evolution of biological networks. To determine if a biological network is robust and/or evolvable, it is required to compare its functions before and after mutations. However, this sometimes takes a high computational cost as the network size grows. Here, we develop a predictive method to estimate the robustness and evolvability of biological networks without an explicit comparison of functions. We measure antifragility in Boolean network models of biological systems and use this as the predictor. Antifragility occurs when a system benefits from external perturbations. By means of the differences of antifragility between the original and mutated biological networks, we train a convolutional neural network (CNN) and test it to classify the properties of robustness and evolvability. We found that our CNN model successfully classified the properties. Thus, we conclude that our antifragility measure can be used as a predictor of the robustness and evolvability of biological networks.

scholarly journals Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections

1992 ◽  
Vol 4 (1) ◽  
pp. 108-119 ◽  
Author(s):  
K. P. Unnikrishnan ◽  
J. J. Hopfield ◽  
D. W. Tank
Keyword(s):  
Neural Network ◽  
Time Delays ◽  
Network Size ◽  
Data Driven ◽  
Digit Recognition ◽  
Feature Detectors ◽  
Self Recognition ◽  
Speaker Independent ◽  
New Ideas ◽  
Natural Classes

The capability of a small neural network to perform speaker-independent recognition of spoken digits in connected speech has been investigated. The network uses time delays to organize rapidly changing outputs of symbol detectors over the time scale of a word. The network is data driven and unclocked. To achieve useful accuracy in a speaker-independent setting, many new ideas and procedures were developed. These include improving the feature detectors, self-recognition of word ends, reduction in network size, and dividing speakers into natural classes. Quantitative experiments based on Texas Instruments (TI) digit databases are described.

Control Oriented Modelling of Engine IMEP Variation

2016 ◽  
Author(s):  
Qilun Zhu ◽  
Robert Prucka ◽  
Shu Wang ◽  
Michael Prucka ◽  
Hussein Dourra
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Turbulent Combustion ◽  
Single Layer ◽  
Network Size ◽  
Operating Conditions ◽  
Premixed Turbulent Combustion ◽  
Spark Timing ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Engine cycle-by-cycle combustion variation is a potential source of emissions and drivability issues in automobiles, and has become an important concern for engine control engineers. The nature of turbulent combustion in IC engines means that combustion variations cannot be eliminated completely. Furthermore, it is inevitable for the engine to run at conditions with high combustion variations in most vehicle applications. For example, during gear shifts spark timing can be changed dramatically to help track the fast transitions of torque demand, often resulting in high Coefficient of Variation in Indicated Mean Effective Pressure (COV of IMEP). Under these circumstances, the control engineers have to weigh between combustion variation and other performance demands (i.e. fast torque tracking). An accurate online estimation of COV of IMEP can be beneficial to this process. A calibrated map of COV of IMEP versus engine operating conditions can be an option for engines with few control actuators. As the number of control actuators increases, combustion variation modelling using inputs with physical representations becomes favorable due to the potential for reduced calibration effort. However, since COV of IMEP is a stochastic variable describing the distribution of IMEP output, it can only be modelled empirically. This research proposes a control-oriented real-time COV of IMEP model based on an Artificial Neural Network (ANN) and inputs from turbulent combustion research. The effects of premixed turbulent combustion variation are analyzed with flame regime analysis in this research after a brief introduction of the experimental setup and engine information. In-cylinder thermodynamics are then evaluated to reveal how the changes of heat release transform into the variation of cylinder pressure, producing COV of IMEP. A range of model input parameters are assessed to determine the set that produces the most accurate prediction of IMEP variation with minimal computational requirements. An Artificial Neural Network (ANN) is applied to capture the nonlinear coupled correlations between COV of IMEP and model inputs. The ANN is combined with a regression pretreatment to reduce network size and improve extrapolation stability. This computationally efficient single-layer three-neuron ANN COV of IMEP model achieved 0.29% normalized Root Mean Square Error (RMSE). Dynamometer tests show that the model performs well outside the training region.

Sign in / Sign up

Export Citation Format

Share Document