Feedforward neural network
View article: Transformers are Universal Approximators of Sequence-to-Sequence Functions
Transformers are Universal Approximators of Sequence-to-Sequence Functions Open
This paper investigates the capacity of Transformer networks to approximate any continuous sequence-to-sequence function. We present a theoretical framework demonstrating that Transformers, with sufficient architectural capacity, can unifo…
View article: Transformers are Universal Approximators of Sequence-to-Sequence Functions
Transformers are Universal Approximators of Sequence-to-Sequence Functions Open
This paper investigates the capacity of Transformer networks to approximate any continuous sequence-to-sequence function. We present a theoretical framework demonstrating that Transformers, with sufficient architectural capacity, can unifo…
View article: Concentrations of Plant Protection Product Metabolites in Groundwater in Germany: Assessing the Influence of Site Characteristics using Random Forests and Feedforward Neural Networks
Concentrations of Plant Protection Product Metabolites in Groundwater in Germany: Assessing the Influence of Site Characteristics using Random Forests and Feedforward Neural Networks Open
This repository accompanies the manuscript “Concentrations of Plant Protection Product Metabolites in Groundwater in Germany: Assessing the Influence of Site Characteristics using Random Forests and Feedforward Neural Networks” by Cooke, A…
View article: Concentrations of Plant Protection Product Metabolites in Groundwater in Germany: Assessing the Influence of Site Characteristics using Random Forests and Feedforward Neural Networks
Concentrations of Plant Protection Product Metabolites in Groundwater in Germany: Assessing the Influence of Site Characteristics using Random Forests and Feedforward Neural Networks Open
This repository accompanies the manuscript “Concentrations of Plant Protection Product Metabolites in Groundwater in Germany: Assessing the Influence of Site Characteristics using Random Forests and Feedforward Neural Networks” by Cooke, A…
View article: Preserved Neural Dynamics across Arm- and Brain-controlled Movements
Preserved Neural Dynamics across Arm- and Brain-controlled Movements Open
The neural response for motor control is complex and dynamic; it has been found to dramatically transit from planning to executing movements. As brain-machine interfaces (BMIs) can directly connect the brain and the external world by yield…
View article: "10 Human Participants Gait Data collected outdoors from two smartwatches placed on each wrist"
"10 Human Participants Gait Data collected outdoors from two smartwatches placed on each wrist" Open
"Assistive robotic systems are crucial in healthcare; however, their safe adoption is hindered by traditional authentication methods that present significant usability challenges. Assistive robots must authenticate users continuously witho…
View article: NOISE-RESILIENT DUPLICATE RECORD DETECTION IN MULTI-SOURCE PRODUCT DATABASES USING SIAMESE DEEP NETWORKS AND GRADIENT-BOOSTED MODELS
NOISE-RESILIENT DUPLICATE RECORD DETECTION IN MULTI-SOURCE PRODUCT DATABASES USING SIAMESE DEEP NETWORKS AND GRADIENT-BOOSTED MODELS Open
Title: NOISE-RESILIENT DUPLICATE RECORD DETECTION IN MULTI-SOURCE PRODUCT DATABASES USING SIAMESE DEEP NETWORKS AND GRADIENT-BOOSTED MODELS Keywords - Duplicate Detection; Machine Learning; Deep Learning; Siamese Network; Data Quality; Noi…
View article: NOISE-RESILIENT DUPLICATE RECORD DETECTION IN MULTI-SOURCE PRODUCT DATABASES USING SIAMESE DEEP NETWORKS AND GRADIENT-BOOSTED MODELS
NOISE-RESILIENT DUPLICATE RECORD DETECTION IN MULTI-SOURCE PRODUCT DATABASES USING SIAMESE DEEP NETWORKS AND GRADIENT-BOOSTED MODELS Open
Title: NOISE-RESILIENT DUPLICATE RECORD DETECTION IN MULTI-SOURCE PRODUCT DATABASES USING SIAMESE DEEP NETWORKS AND GRADIENT-BOOSTED MODELS Keywords - Duplicate Detection; Machine Learning; Deep Learning; Siamese Network; Data Quality; Noi…
View article: A transfer learning approach for automatic conflicts detection in software requirement sentence pairs based on dual encoders
A transfer learning approach for automatic conflicts detection in software requirement sentence pairs based on dual encoders Open
Software Requirement Document (RD) typically contain tens of thousands of individual requirements, and ensuring consistency among these requirements is critical for the success of software engineering projects. Automated detection methods …
View article: A transfer learning approach for automatic conflicts detection in software requirement sentence pairs based on dual encoders
A transfer learning approach for automatic conflicts detection in software requirement sentence pairs based on dual encoders Open
Software Requirement Document (RD) typically contain tens of thousands of individual requirements, and ensuring consistency among these requirements is critical for the success of software engineering projects. Automated detection methods …
View article: G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networks
G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networks Open
We propose a novel randomized algorithm for constructing binary neural networks with tunable accuracy. This approach is motivated by hyperdimensional computing (HDC), which is a brain-inspired paradigm that leverages high-dimensional vecto…
View article: Explainable Deep Learning for Secrecy Energy-Efficiency Maximization in Ambient Backscatter Multi-User NOMA Systems
Explainable Deep Learning for Secrecy Energy-Efficiency Maximization in Ambient Backscatter Multi-User NOMA Systems Open
In this paper, we investigate the secrecy energy-efficiency (SEE) of a multi-user downlink non-orthogonal multiple access (NOMA) system assisted by multiple ambient backscatter communications (AmBC) in the presence of a passive eavesdroppe…
View article: ALIS v5.0: Unified Cognitive AI Framework
ALIS v5.0: Unified Cognitive AI Framework Open
ALIS v5.0: A Unified Cognitive AI Framework This paper introduces ALIS (Artificial Learning Intelligence System), a novel theoretical framework for artificial intelligence and human cognition based on spectral timbre sequences and binary d…
View article: Solving Heterogeneous Agent Models with Physics-informed Neural Networks
Solving Heterogeneous Agent Models with Physics-informed Neural Networks Open
Understanding household behaviour is essential for modelling macroeconomic dynamics and designing effective policy. While heterogeneous agent models offer a more realistic alternative to representative agent frameworks, their implementatio…
View article: ALIS v5.0: Unified Cognitive AI Framework
ALIS v5.0: Unified Cognitive AI Framework Open
ALIS v5.0: A Unified Cognitive AI Framework This paper introduces ALIS (Artificial Learning Intelligence System), a novel theoretical framework for artificial intelligence and human cognition based on spectral timbre sequences and binary d…
View article: Explainable Deep Learning for Secrecy Energy-Efficiency Maximization in Ambient Backscatter Multi-User NOMA Systems
Explainable Deep Learning for Secrecy Energy-Efficiency Maximization in Ambient Backscatter Multi-User NOMA Systems Open
In this paper, we investigate the secrecy energy-efficiency (SEE) of a multi-user downlink non-orthogonal multiple access (NOMA) system assisted by multiple ambient backscatter communications (AmBC) in the presence of a passive eavesdroppe…
View article: Event-Triggered Neural Network Multivariate Control for Wastewater Treatment Process
Event-Triggered Neural Network Multivariate Control for Wastewater Treatment Process Open
Recently, the neural network control has been widely used in the field of wastewater treatment process (WWTP). However, most neural network (NN) control methods are time-driven, with a large number of transmissions and a large amount of ne…
View article: Solving Heterogeneous Agent Models with Physics-informed Neural Networks
Solving Heterogeneous Agent Models with Physics-informed Neural Networks Open
Understanding household behaviour is essential for modelling macroeconomic dynamics and designing effective policy. While heterogeneous agent models offer a more realistic alternative to representative agent frameworks, their implementatio…
View article: Active Learning for Physics-Informed Digital Twins of Integrated Thermal Energy Distribution Systems
Active Learning for Physics-Informed Digital Twins of Integrated Thermal Energy Distribution Systems Open
The Thermal Energy Distribution System (TEDS) at Idaho National Laboratory (INL) provides a unique experimental platform for testing advanced supervisory control strategies in hybrid energy systems that combine renewable, nuclear, and ther…
View article: Estimation of Solar Energy Production Data from Renewable Energy Sources Using ANN Method and Presenting It to the Public Benefit
Estimation of Solar Energy Production Data from Renewable Energy Sources Using ANN Method and Presenting It to the Public Benefit Open
Nowadays, the use of renewable energy sources in electricity generation is gradually increasing compared to non-renewable sources, and artificial intelligence algorithms are effectively used in energy forecasting. In this study, a multi-la…
View article: A feedforward equalizer with selective noise decorrelation for bandwidth-limited signal
A feedforward equalizer with selective noise decorrelation for bandwidth-limited signal Open
View article: Analysis of the Effectiveness of Data Warehousing in Management Information Systems Using the Neural Networks Method
Analysis of the Effectiveness of Data Warehousing in Management Information Systems Using the Neural Networks Method Open
Purpose: The purpose of this research is to investigate the effectiveness of data warehousing and the application of Neural Networks methods in analyzing bicycle travel app user data, with a focus on enhancing the annual membership of app …
View article: Integrating Large Language Models with Machine Learning for Explainable Banking Security and Financial Risk Assessment
Integrating Large Language Models with Machine Learning for Explainable Banking Security and Financial Risk Assessment Open
This study proposes and empirically evaluates a hybrid banking security framework that integrates traditional machine learning models with a large language model (LLM) for enhanced risk assessment and decision support. Using two open-sourc…
View article: Comparative Analysis of Parametric and Neural Network Models for Rural Highway Traffic Volume Prediction
Comparative Analysis of Parametric and Neural Network Models for Rural Highway Traffic Volume Prediction Open
The information and communication technology revolution has provided researchers with new opportunities to enhance traffic prediction methods. Accurate long-term traffic forecasts are essential for sustainable infrastructure planning, supp…
View article: Neural encoding of innate preference to gravity-defying motion
Neural encoding of innate preference to gravity-defying motion Open
The dataset includes analyses of the neural activity in young domestic chicks responding to the upward and downward moving objects. AllRecordingsSorted - all neural recordings including unit number, spike times per trial, trial info (Direc…
View article: Neural encoding of innate preference to gravity-defying motion
Neural encoding of innate preference to gravity-defying motion Open
The dataset includes analyses of the neural activity in young domestic chicks responding to the upward and downward moving objects. AllRecordingsSorted - all neural recordings including unit number, spike times per trial, trial info (Direc…
View article: Fourier Series and the Spectral Bias of Neural Networks
Fourier Series and the Spectral Bias of Neural Networks Open
The success of neural networks in approximating complex functions across various domains is undeniable, yet the mechanisms governing their learning dynamics remain an active area of research. One prominent phenomenon observed in the traini…
View article: Fourier Series and the Spectral Bias of Neural Networks
Fourier Series and the Spectral Bias of Neural Networks Open
The success of neural networks in approximating complex functions across various domains is undeniable, yet the mechanisms governing their learning dynamics remain an active area of research. One prominent phenomenon observed in the traini…
View article: A novel deep learning-based control for voltage sag prediction and DVR–LVRT coordination in grid-connected wind turbine systems
A novel deep learning-based control for voltage sag prediction and DVR–LVRT coordination in grid-connected wind turbine systems Open
This study proposes a novel deep feedforward neural network (DFNN)-based control for voltage sag prediction and dynamic voltage restorer (DVR) integration with low-voltage ride-through (LVRT) to improve voltage stability and energy efficie…
View article: Fourier Series and the Spectral Bias of Neural Networks
Fourier Series and the Spectral Bias of Neural Networks Open
The success of neural networks in approximating complex functions across various domains is undeniable, yet the mechanisms governing their learning dynamics remain an active area of research. One prominent phenomenon observed in the traini…