scholarly journals Improved supervised learning methods for EoR parameters reconstruction

2019 ◽  
Vol 490 (1) ◽  
pp. 371-384 ◽  
Author(s):  
Aristide Doussot ◽  
Evan Eames ◽  
Benoit Semelin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bayesian Inference ◽  
Maximum Likelihood ◽  
Supervised Learning ◽  
Confidence Level ◽  
Thermal Noise ◽  
Model Parameters ◽  
Learning Methods ◽  
Parameter Values

ABSTRACT Within the next few years, the Square Kilometre Array (SKA) or one of its pathfinders will hopefully detect the 21-cm signal fluctuations from the Epoch of Reionization (EoR). Then, the goal will be to accurately constrain the underlying astrophysical parameters. Currently, this is mainly done with Bayesian inference. Recently, neural networks have been trained to perform inverse modelling and, ideally, predict the maximum-likelihood values of the model parameters. We build on these by improving the accuracy of the predictions using several supervised learning methods: neural networks, kernel regressions, or ridge regressions. Based on a large training set of 21-cm power spectra, we compare the performances of these methods. When using a noise-free signal generated by the model itself as input, we improve on previous neural network accuracy by one order of magnitude and, using a local ridge kernel regression, we gain another factor of a few. We then reach an accuracy level on the reconstruction of the maximum-likelihood parameter values of a few per cents compared the 1σ confidence level due to SKA thermal noise (as estimated with Bayesian inference). For an input signal affected by an SKA-like thermal noise but constrained to yield the same maximum-likelihood parameter values as the noise-free signal, our neural network exhibits an error within half of the 1σ confidence level due to the SKA thermal noise. This accuracy improves to 10$\, {\rm per\, cent}$ of the 1σ level when using the local ridge kernel. We are thus reaching a performance level where supervised learning methods are a viable alternative to determine the maximum-likelihood parameters values.

scholarly journals Robust and fast post-processing of single-shot spin qubit detection events with a neural network

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tom Struck ◽  
Javed Lindner ◽  
Arne Hollmann ◽  
Floyd Schauer ◽  
Andreas Schmidbauer ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bayesian Inference ◽  
Rabi Oscillation ◽  
Detection Methods ◽  
Measured Signal ◽  
Single Shot ◽  
Post Processing ◽  
Readout Signal ◽  
Spin Qubit

AbstractEstablishing low-error and fast detection methods for qubit readout is crucial for efficient quantum error correction. Here, we test neural networks to classify a collection of single-shot spin detection events, which are the readout signal of our qubit measurements. This readout signal contains a stochastic peak, for which a Bayesian inference filter including Gaussian noise is theoretically optimal. Hence, we benchmark our neural networks trained by various strategies versus this latter algorithm. Training of the network with 106 experimentally recorded single-shot readout traces does not improve the post-processing performance. A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter. This neural network turns out to be more robust to fluctuations in the signal offset, length and delay as well as in the signal-to-noise ratio. Notably, we find an increase of 7% in the visibility of the Rabi oscillation when we employ a network trained by synthetic readout traces combined with measured signal noise of our setup. Our contribution thus represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.

scholarly journals Generalized Born radii computation using linear models and neural networks

2019 ◽  
Vol 36 (6) ◽  
pp. 1757-1764
Author(s):  
Saida Saad Mohamed Mahmoud ◽  
Gennaro Esposito ◽  
Giuseppe Serra ◽  
Federico Fogolari
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Linear Model ◽  
Correlation Coefficient ◽  
Linear Models ◽  
Reference Method ◽  
Supplementary Information ◽  
Model Parameters ◽  
Generalized Born ◽  
Supplementary Material

Abstract Motivation Implicit solvent models play an important role in describing the thermodynamics and the dynamics of biomolecular systems. Key to an efficient use of these models is the computation of generalized Born (GB) radii, which is accomplished by algorithms based on the electrostatics of inhomogeneous dielectric media. The speed and accuracy of such computations are still an issue especially for their intensive use in classical molecular dynamics. Here, we propose an alternative approach that encodes the physics of the phenomena and the chemical structure of the molecules in model parameters which are learned from examples. Results GB radii have been computed using (i) a linear model and (ii) a neural network. The input is the element, the histogram of counts of neighbouring atoms, divided by atom element, within 16 Å. Linear models are ca. 8 times faster than the most widely used reference method and the accuracy is higher with correlation coefficient with the inverse of ‘perfect’ GB radii of 0.94 versus 0.80 of the reference method. Neural networks further improve the accuracy of the predictions with correlation coefficient with ‘perfect’ GB radii of 0.97 and ca. 20% smaller root mean square error. Availability and implementation We provide a C program implementing the computation using the linear model, including the coefficients appropriate for the set of Bondi radii, as Supplementary Material. We also provide a Python implementation of the neural network model with parameter and example files in the Supplementary Material as well. Supplementary information Supplementary data are available at Bioinformatics online.

SAS Nonlinear Models or Artificial Higher Order Neural Network Nonlinear Models?

2021 ◽  
pp. 174-217
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Data Analysis ◽  
Learning Algorithm ◽  
Nonlinear Models ◽  
Higher Order ◽  
Model Order ◽  
Higher Order Neural Networks ◽  
Parameter Values ◽  
Better Than

This chapter delivers general format of higher order neural networks (HONNs) for nonlinear data analysis and six different HONN models. Then, this chapter mathematically proves that HONN models could converge and have mean squared errors close to zero. Moreover, this chapter illustrates the learning algorithm with update formulas. HONN models are compared with SAS nonlinear (NLIN) models, and results show that HONN models are 3 to 12% better than SAS nonlinear models. Finally, this chapter shows how to use HONN models to find the best model, order, and coefficients without writing the regression expression, declaring parameter names, and supplying initial parameter values.

scholarly journals Distinguishing Felsenstein Zone from Farris Zone Using Neural Networks

2020 ◽  
Vol 37 (12) ◽  
pp. 3632-3641
Author(s):  
Alina F Leuchtenberger ◽  
Stephen M Crotty ◽  
Tamara Drucks ◽  
Heiko A Schmidt ◽  
Sebastian Burgstaller-Muehlbacher ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Maximum Likelihood ◽  
Phylogenetic Tree ◽  
Maximum Parsimony ◽  
Reconstruction Method ◽  
Long Branch Attraction ◽  
Tree Reconstruction ◽  
Phylogenetic Tree Reconstruction ◽  
The Neural Network

Abstract Maximum likelihood and maximum parsimony are two key methods for phylogenetic tree reconstruction. Under certain conditions, each of these two methods can perform more or less efficiently, resulting in unresolved or disputed phylogenies. We show that a neural network can distinguish between four-taxon alignments that were evolved under conditions susceptible to either long-branch attraction or long-branch repulsion. When likelihood and parsimony methods are discordant, the neural network can provide insight as to which tree reconstruction method is best suited to the alignment. When applied to the contentious case of Strepsiptera evolution, our method shows robust support for the current scientific view, that is, it places Strepsiptera with beetles, distant from flies.

scholarly journals Effects of Different Feature Parameters of sEMG on Human Motion Pattern Recognition Using Multilayer Perceptrons and LSTM Neural Networks

2020 ◽  
Vol 10 (10) ◽  
pp. 3358 ◽  
Author(s):  
Jiyuan Song ◽  
Aibin Zhu ◽  
Yao Tu ◽  
Hu Huang ◽  
Muhammad Affan Arif ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Pattern Recognition ◽  
Human Motion ◽  
Control Mode ◽  
Multilayer Perceptrons ◽  
Model Parameters ◽  
Motion Pattern ◽  
Accuracy Rate ◽  
Feature Parameters

In response to the need for an exoskeleton to quickly identify the wearer’s movement mode in the mixed control mode, this paper studies the impact of different feature parameters of the surface electromyography (sEMG) signal on the accuracy of human motion pattern recognition using multilayer perceptrons and long short-term memory (LSTM) neural networks. The sEMG signals are extracted from the seven common human motion patterns in daily life, and the time domain and frequency domain features are extracted to build a feature parameter dataset for training the classifier. Recognition of human lower extremity movement patterns based on multilayer perceptrons and the LSTM neural network were carried out, and the final recognition accuracy rates of different feature parameters and different classifier model parameters were compared in the process of establishing the dataset. The experimental results show that the best accuracy rate of human motion pattern recognition using multilayer perceptrons is 95.53%, and the best accuracy rate of human motion pattern recognition using the LSTM neural network is 96.57%.

scholarly journals 21SSD: a new public 21-cm EoR database

2017 ◽  
Vol 12 (S333) ◽  
pp. 30-33
Author(s):  
Evan Eames ◽  
Benoît Semelin
Keyword(s):  
Neural Networks ◽  
High Resolution ◽  
Thermal Noise ◽  
Power Spectra ◽  
Distribution Functions ◽  
Hydrodynamic Simulation ◽  
Crucial Step ◽  
New Public ◽  
Parameter Values ◽  
Fully Coupled

AbstractWith current efforts inching closer to detecting the 21-cm signal from the Epoch of Reionization (EoR), proper preparation will require publicly available simulated models of the various forms the signal could take. In this work we present a database of such models, available at 21ssd.obspm.fr. The models are created with a fully-coupled radiative hydrodynamic simulation (LICORICE), and are created at high resolution (10243). We also begin to analyse and explore the possible 21-cm EoR signals (with Power Spectra and Pixel Distribution Functions), and study the effects of thermal noise on our ability to recover the signal out to high redshifts. Finally, we begin to explore the concepts of ‘distance’ between different models, which represents a crucial step towards optimising parameter space sampling, training neural networks, and finally extracting parameter values from observations.

scholarly journals NEURAL NETWORK INVERSION OF RESISTIVITY DATA FOR DETERMINATION OF DISTANCE TO A BED BOUNDARY

2021 ◽  
Vol 2 (2) ◽  
pp. 95-102
Author(s):  
Dmitry Yu. Kushnir ◽  
Nikolay N. Velker ◽  
Darya V. Andornaya ◽  
Yuriy E. Antonov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Estimation ◽  
Model Parameters ◽  
Formation Model ◽  
Inversion Algorithm ◽  
Resistivity Data ◽  
Neural Network Inversion ◽  
Real Time Estimation

Accurate real-time estimation of a distance to the nearest bed boundary simplifies the steering of directional wells. For estimation of that distance, we propose an approach of pointwise inversion of resistivity data using neural networks based on two-layer resistivity formation model. The model parameters are determined from the tool responses using a cascade of neural networks. The first network calculates the resistivity of the layer containing the tool measure point. The subsequent networks take as input the tool responses and the model parameters determined with the previous networks. All networks are trained on the same synthetic database. The samples of that database consist of the pairs of model parameters and corresponding noisy tool responses. The results of the proposed approach are close to the results of the general inversion algorithm based on the method of the most-probable parameter combination. At the same time, the performance of the proposed inversion is several orders faster.

scholarly journals Interpolation Consistency Training for Semi-supervised Learning

2019 ◽  
Author(s):  
Vikas Verma ◽  
Alex Lamb ◽  
Juho Kannala ◽  
Yoshua Bengio ◽  
David Lopez-Paz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Supervised Learning ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Data Distribution ◽  
Network Architectures ◽  
Low Density ◽  
Decision Boundary ◽  
Classification Problems

We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark dataset.

scholarly journals Building robust neural networks using different loss functions

2021 ◽  
pp. 67-82
Author(s):  
Maria Sivak ◽  
◽  
Vladimir Timofeev ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Loss Function ◽  
Back Propagation ◽  
Loss Functions ◽  
Back Propagation Algorithm ◽  
Error Back Propagation ◽  
Propagation Algorithm ◽  
Error Back Propagation Algorithm ◽  
Parameter Values

The paper considers the problem of building robust neural networks using different robust loss functions. Applying such neural networks is reasonably when working with noisy data, and it can serve as an alternative to data preprocessing and to making neural network architecture more complex. In order to work adequately, the error back-propagation algorithm requires a loss function to be continuously or two-times differentiable. According to this requirement, two five robust loss functions were chosen (Andrews, Welsch, Huber, Ramsey and Fair). Using the above-mentioned functions in the error back-propagation algorithm instead of the quadratic one allows obtaining an entirely new class of neural networks. For investigating the properties of the built networks a number of computational experiments were carried out. Different values of outliers’ fraction and various numbers of epochs were considered. The first step included adjusting the obtained neural networks, which lead to choosing such values of internal loss function parameters that resulted in achieving the highest accuracy of a neural network. To determine the ranges of parameter values, a preliminary study was pursued. The results of the first stage allowed giving recommendations on choosing the best parameter values for each of the loss functions under study. The second stage dealt with comparing the investigated robust networks with each other and with the classical one. The analysis of the results shows that using the robust technique leads to a significant increase in neural network accuracy and in a learning rate.

Sign in / Sign up

Export Citation Format

Share Document