scholarly journals Contextual Regression: An Accurate and Conveniently Interpretable Nonlinear Model for Mining Discovery from Scientific Data

2017 ◽  
Author(s):  
Chengyu Liu ◽  
Wei Wang
Keyword(s):  
Neural Network ◽  
Scientific Discovery ◽  
Nonlinear Modeling ◽  
Random Noise ◽  
Simulated Data ◽  
Product Layer ◽  
Scientific Data ◽  
Machine Learning Algorithms ◽  
Open Chromatin ◽  
Hybrid Architecture

AbstractMachine learning algorithms such as linear regression, SVM and neural network have played an increasingly important role in the process of scientific discovery. However, none of them is both interpretable and accurate on nonlinear datasets. Here we present contextual regression, a method that joins these two desirable properties together using a hybrid architecture of neural network embedding and dot product layer. We demonstrate its high prediction accuracy and sensitivity through the task of predictive feature selection on a simulated dataset and the application of predicting open chromatin sites in the human genome. On the simulated data, our method achieved high fidelity recovery of feature contributions under random noise levels up to ±200%. On the open chromatin dataset, the application of our method not only outperformed the state of the art method in terms of accuracy, but also unveiled two previously unfound open chromatin related histone marks. Our method fills in the gap of accurate and interpretable nonlinear modeling in scientific data mining tasks.

scholarly journals Development of a fully connected residual neural network for directional gamma ray detection

2020 ◽  
Vol 50 ◽  
pp. 2060010
Author(s):  
Matthew Durbin ◽  
Christopher Balbier ◽  
Azaree Lintereur
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Gamma Ray ◽  
Simulated Data ◽  
Machine Learning Algorithms ◽  
Well Performance ◽  
Large Area ◽  
Area Source ◽  
Directional Detection ◽  
Fully Connected

Directional detection plays an important role in the search for rogue or illicit radioactive sources but is often complicated by Poisson statistics, large distances, and various sources of noise. A currently used directional detection method involves extracting the angular information of a source’s location from a cluster of detectors in a set geometry. Traditional algorithms designed to process detected data typically involve performing a least squares assessment against a database prepopulated with detector responses of known source locations. These algorithms perform best when the standoff distance is like that available in the prepopulated database; they lose accuracy when distances and environments of measurements are not well represented in the database. Analysis of highly variable and noisy data can often benefit from the robustness of machine learning, which has been implemented in applications such as isotope identification and radium mapping. This work aims to investigate the utility of machine learning algorithms capable of analyzing data with large amounts of statistical variability to improve directional location capabilities for large area source searches. Preliminary results with a fully connected residual neural network include the successful source location for simulated search scenarios to within 1 degree in 24% of trials. The same simulated data analyzed using traditional methods resulted in 1 degree location for 11% of trials. The traditional and neural network algorithms were compared in terms of error and accuracy as well performance as a function of distance for a simulated dataset of source searches. Results indicate that more robust algorithms, such as the implemented neural network, can improve system-inherent accuracy and over all directional capabilities.

Improving the effectiveness of traditional education based on computer artificial intelligence and neural network system

2020 ◽  
pp. 1-11
Author(s):  
Wenjuan Ma ◽  
Xuesi Zhao ◽  
Yuxiu Guo
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Education Reform ◽  
Traditional Education ◽  
Machine Learning Algorithms ◽  
Local Optimum ◽  
Optimization Strategy ◽  
Fish School ◽  
Tlbo Algorithm ◽  
Neural Network System

The application of artificial intelligence and machine learning algorithms in education reform is an inevitable trend of teaching development. In order to improve the teaching intelligence, this paper builds an auxiliary teaching system based on computer artificial intelligence and neural network based on the traditional teaching model. Moreover, in this paper, the optimization strategy is adopted in the TLBO algorithm to reduce the running time of the algorithm, and the extracurricular learning mechanism is introduced to increase the adjustable parameters, which is conducive to the algorithm jumping out of the local optimum. In addition, in this paper, the crowding factor in the fish school algorithm is used to define the degree or restraint of teachers’ control over students. At the same time, students in the crowded range gather near the teacher, and some students who are difficult to restrain perform the following behavior to follow the top students. Finally, this study builds a model based on actual needs, and designs a control experiment to verify the system performance. The results show that the system constructed in this paper has good performance and can provide a theoretical reference for related research.

scholarly journals Data-Driven Stability Assessment of Multilayer Long Short-Term Memory Networks

2021 ◽  
Vol 11 (4) ◽  
pp. 1829
Author(s):  
Davide Grande ◽  
Catherine A. Harris ◽  
Giles Thomas ◽  
Enrico Anderlini
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Short Term Memory ◽  
Moving Average ◽  
Machine Learning Algorithms ◽  
Physical Models ◽  
Data Driven ◽  
The Stability ◽  
And Control ◽  
Nonlinear Autoregressive

Recurrent Neural Networks (RNNs) are increasingly being used for model identification, forecasting and control. When identifying physical models with unknown mathematical knowledge of the system, Nonlinear AutoRegressive models with eXogenous inputs (NARX) or Nonlinear AutoRegressive Moving-Average models with eXogenous inputs (NARMAX) methods are typically used. In the context of data-driven control, machine learning algorithms are proven to have comparable performances to advanced control techniques, but lack the properties of the traditional stability theory. This paper illustrates a method to prove a posteriori the stability of a generic neural network, showing its application to the state-of-the-art RNN architecture. The presented method relies on identifying the poles associated with the network designed starting from the input/output data. Providing a framework to guarantee the stability of any neural network architecture combined with the generalisability properties and applicability to different fields can significantly broaden their use in dynamic systems modelling and control.

scholarly journals New Results on Radioactive Mixture Identification and Relative Count Contribution Estimation

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4155
Author(s):  
Bulent Ayhan ◽  
Chiman Kwan
Keyword(s):  
Deep Learning ◽  
Noise Source ◽  
Simulated Data ◽  
Nuclear Material ◽  
Machine Learning Algorithms ◽  
Detector Response ◽  
Nuclear Materials ◽  
Ratio Estimation ◽  
Analysis Software ◽  
Detector Distance

Detecting nuclear materials in mixtures is challenging due to low concentration, environmental factors, sensor noise, source-detector distance variations, and others. This paper presents new results on nuclear material identification and relative count contribution (also known as mixing ratio) estimation for mixtures of materials in which there are multiple isotopes present. Conventional and deep-learning-based machine learning algorithms were compared. Realistic simulated data using Gamma Detector Response and Analysis Software (GADRAS) were used in our comparative studies. It was observed that a deep learning approach is highly promising.

Betalogger: Smartphone Sensor-based Side-channel Attack Detection and Text Inference Using Language Modeling and Dense MultiLayer Neural Network

2021 ◽  
Vol 20 (5) ◽  
pp. 1-17
Author(s):  
Abdul Rehman Javed ◽  
Saif Ur Rehman ◽  
Mohib Ullah Khan ◽  
Mamoun Alazab ◽  
Habib Ullah Khan
Keyword(s):  
Neural Network ◽  
Language Modeling ◽  
Attack Detection ◽  
Machine Learning Algorithms ◽  
Second Phase ◽  
Sensitive Data ◽  
Phase Sequence ◽  
Smartphone Technology ◽  
Conventional Machine ◽  
Sequence Generator

With the recent advancement of smartphone technology in the past few years, smartphone usage has increased on a tremendous scale due to its portability and ability to perform many daily life tasks. As a result, smartphones have become one of the most valuable targets for hackers to perform cyberattacks, since the smartphone can contain individuals’ sensitive data. Smartphones are embedded with highly accurate sensors. This article proposes BetaLogger , an Android-based application that highlights the issue of leaking smartphone users’ privacy using smartphone hardware sensors (accelerometer, magnetometer, and gyroscope). BetaLogger efficiently infers the typed text (long or short) on a smartphone keyboard using Language Modeling and a Dense Multi-layer Neural Network (DMNN). BetaLogger is composed of two major phases: In the first phase, Text Inference Vector is given as input to the DMNN model to predict the target labels comprising the alphabet, and in the second phase, sequence generator module generate the output sequence in the shape of a continuous sentence. The outcomes demonstrate that BetaLogger generates highly accurate short and long sentences, and it effectively enhances the inference rate in comparison with conventional machine learning algorithms and state-of-the-art studies.

Internet financial supervision based on machine learning and improved neural network

2020 ◽  
pp. 1-12
Author(s):  
Cao Yanli
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Credit Risk ◽  
Machine Learning Algorithms ◽  
Financial Supervision ◽  
Loan Pricing ◽  
Comprehensive Management ◽  
Risk Pricing ◽  
Basel Agreement ◽  
Relevant Factors

The research on the risk pricing of Internet finance online loans not only enriches the theory and methods of online loan pricing, but also helps to improve the level of online loan risk pricing. In order to improve the efficiency of Internet financial supervision, this article builds an Internet financial supervision system based on machine learning algorithms and improved neural network algorithms. Moreover, on the basis of factor analysis and discretization of loan data, this paper selects the relatively mature Logistic regression model to evaluate the credit risk of the borrower and considers the comprehensive management of credit risk and the matching with income. In addition, according to the relevant provisions of the New Basel Agreement on expected losses and economic capital, starting from the relevant factors, this article combines the credit risk assessment results to obtain relevant factors through regional research and conduct empirical analysis. The research results show that the model constructed in this paper has certain reliability.

scholarly journals Spectral Convolution Feature-Based SPD Matrix Representation for Signal Detection Using a Deep Neural Network

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 949
Author(s):  
Jiangyi Wang ◽  
Min Liu ◽  
Xinwu Zeng ◽  
Xiaoqiang Hua
Keyword(s):  
Neural Network ◽  
Signal Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Detection Method ◽  
Learning Algorithm ◽  
Simulated Data ◽  
Data Sets ◽  
Feature Maps ◽  
Simulated Data Sets

Convolutional neural networks have powerful performances in many visual tasks because of their hierarchical structures and powerful feature extraction capabilities. SPD (symmetric positive definition) matrix is paid attention to in visual classification, because it has excellent ability to learn proper statistical representation and distinguish samples with different information. In this paper, a deep neural network signal detection method based on spectral convolution features is proposed. In this method, local features extracted from convolutional neural network are used to construct the SPD matrix, and a deep learning algorithm for the SPD matrix is used to detect target signals. Feature maps extracted by two kinds of convolutional neural network models are applied in this study. Based on this method, signal detection has become a binary classification problem of signals in samples. In order to prove the availability and superiority of this method, simulated and semi-physical simulated data sets are used. The results show that, under low SCR (signal-to-clutter ratio), compared with the spectral signal detection method based on the deep neural network, this method can obtain a gain of 0.5–2 dB on simulated data sets and semi-physical simulated data sets.

Deep learning for denoising

Geophysics ◽  
2019 ◽  
Vol 84 (6) ◽  
pp. V333-V350 ◽  
Author(s):  
Siwei Yu ◽  
Jianwei Ma ◽  
Wenlong Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Graphics Processing Unit ◽  
Random Noise ◽  
Stochastic Gradient Descent ◽  
Processing Unit ◽  
Noise Attenuation ◽  
Optimal Parameters ◽  
Training Set ◽  
Unknown Variance

Compared with traditional seismic noise attenuation algorithms that depend on signal models and their corresponding prior assumptions, removing noise with a deep neural network is trained based on a large training set in which the inputs are the raw data sets and the corresponding outputs are the desired clean data. After the completion of training, the deep-learning (DL) method achieves adaptive denoising with no requirements of (1) accurate modelings of the signal and noise or (2) optimal parameters tuning. We call this intelligent denoising. We have used a convolutional neural network (CNN) as the basic tool for DL. In random and linear noise attenuation, the training set is generated with artificially added noise. In the multiple attenuation step, the training set is generated with the acoustic wave equation. The stochastic gradient descent is used to solve the optimal parameters for the CNN. The runtime of DL on a graphics processing unit for denoising has the same order as the [Formula: see text]-[Formula: see text] deconvolution method. Synthetic and field results indicate the potential applications of DL in automatic attenuation of random noise (with unknown variance), linear noise, and multiples.

scholarly journals Programmable phase-change metasurfaces on waveguides for multimode photonic convolutional neural network

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Changming Wu ◽  
Heshan Yu ◽  
Seokhyeong Lee ◽  
Ruoming Peng ◽  
Ichiro Takeuchi ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Phase Change ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Phase Change Materials ◽  
Refractive Index Change ◽  
Optical Computing ◽  
Machine Learning Algorithms ◽  
Matrix Vector Multiplication

AbstractNeuromorphic photonics has recently emerged as a promising hardware accelerator, with significant potential speed and energy advantages over digital electronics for machine learning algorithms, such as neural networks of various types. Integrated photonic networks are particularly powerful in performing analog computing of matrix-vector multiplication (MVM) as they afford unparalleled speed and bandwidth density for data transmission. Incorporating nonvolatile phase-change materials in integrated photonic devices enables indispensable programming and in-memory computing capabilities for on-chip optical computing. Here, we demonstrate a multimode photonic computing core consisting of an array of programable mode converters based on on-waveguide metasurfaces made of phase-change materials. The programmable converters utilize the refractive index change of the phase-change material Ge2Sb2Te5 during phase transition to control the waveguide spatial modes with a very high precision of up to 64 levels in modal contrast. This contrast is used to represent the matrix elements, with 6-bit resolution and both positive and negative values, to perform MVM computation in neural network algorithms. We demonstrate a prototypical optical convolutional neural network that can perform image processing and recognition tasks with high accuracy. With a broad operation bandwidth and a compact device footprint, the demonstrated multimode photonic core is promising toward large-scale photonic neural networks with ultrahigh computation throughputs.

scholarly journals A convolutional neural network for estimating synaptic connectivity from spike trains

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Daisuke Endo ◽  
Ryota Kobayashi ◽  
Ramon Bartolo ◽  
Bruno B. Averbeck ◽  
Yasuko Sugase-Miyamoto ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Generalized Linear Model ◽  
Simulated Data ◽  
Spike Trains ◽  
Synaptic Connectivity ◽  
Neuronal Circuits ◽  
Cortical Areas ◽  
Neuronal Spike Trains ◽  
Individual Dataset

AbstractThe recent increase in reliable, simultaneous high channel count extracellular recordings is exciting for physiologists and theoreticians because it offers the possibility of reconstructing the underlying neuronal circuits. We recently presented a method of inferring this circuit connectivity from neuronal spike trains by applying the generalized linear model to cross-correlograms. Although the algorithm can do a good job of circuit reconstruction, the parameters need to be carefully tuned for each individual dataset. Here we present another method using a Convolutional Neural Network for Estimating synaptic Connectivity from spike trains. After adaptation to huge amounts of simulated data, this method robustly captures the specific feature of monosynaptic impact in a noisy cross-correlogram. There are no user-adjustable parameters. With this new method, we have constructed diagrams of neuronal circuits recorded in several cortical areas of monkeys.

Sign in / Sign up

Export Citation Format

Share Document