Results 101 to 110 of about 27,097 (268)

IMPROVEMENTS TO THE BACKPROPAGATION ALGORITHM [PDF]

Annals of the University of Petrosani: Economics, 2012
This paper presents some simple techniques to improve the backpropagation algorithm. Since learning in neural networks is an NP-complete problem and since traditional gradient descent methods are rather slow, many alternatives have been tried in order to accelerate convergence.
openaire   +1 more source

Ecoefficiency Analysis and Regression in Data Conversion for Spiking Neural Network Training

Advanced Intelligent Systems, EarlyView.
The environmental footprint of spiking neural networks is quantified during dataset encoding and training for autonomous driving regression across three benchmarks. Temporal depth emerges as the dominant driver of energy consumption and CO2 emissions, while the accuracy–energy trade‐off proves dataset‐dependent. On conventional hardware, spiking models
Fernando S. Martínez, Raúl Parada, Jordi Casas‐Roma, Laia Subirats   +3 more
wiley   +1 more source

Sports Activity Recognition Using Textile‐Based Sensor Fusion and Complex‐Valued Residual Convolutional Neural Networks

Advanced Intelligent Systems, EarlyView.
Motion artifacts in electrocardiographic signals, conventionally dismissed as noise, are shown to encode discriminative activity information. A smart t‐shirt fusing textile strain sensors with textile ECG electrodes, processed through a complex‐valued residual network, recognizes 12 sport activities.
Nada Al‐azzawi, Munire Sibel Cetin, Asli Tuncay Atalay, Ozgur Atalay, Gökhan Ince   +4 more
wiley   +1 more source

Progressive Training of Hybrid Clipped Rectified Linear Unit for Resilient Convolution Neural Networks

IEEE Access
Convolutional neural networks used in safety-critical systems must remain reliable under hardware-induced faults. Activation clipping is an effective fault-mitigation technique, yet existing approaches face a fundamental trade-off: layer-wise clipping ...
Seyedhamidreza Mousavi, Mohammad Hasan Ahmadilivani, Jaan Raik, Maksim Jenihhin, Masoud Daneshtalab   +4 more
doaj   +1 more source

Bronchoscope Tip Localization With Learned Airway Constraints and an Open Source Simulator

Advanced Intelligent Systems, EarlyView.
BronchoLoc addresses feature‐poor bronchoscopic imaging by combining monocular video with a preoperative CT graph to estimate 3D camera location. A local tracker identifies candidate branches, while a sequence‐aware global module refines the trajectory. Demonstrating sub‐centimeter accuracy across synthetic and phantom datasets, this framework advances
Emanuele Nicotra, James Davies, Bibhu Sharma, Adrienne Ji, Kefan Zhu, Phuoc Thien Phan, Nigel H. Lovell, Thanh Nho Do   +7 more
wiley   +1 more source

Analysis and Prediction of Vertical Office Network Bandwidth Using a Backpropagation-Based Neural Network

Ilkom Jurnal Ilmiah
The digitalization of business and operational processes in vertical offices has transformed work behaviour, creating a critical need for stable internet connectivity to ensure smooth operations.
Muhammad Jamil Asshiddiq, Iffatul Mardhiyah   +1 more
doaj   +1 more source

Vertical NAND Flash Memory‐Based Bayesian Neural Networks With Intrinsic Gaussian Weight Sampling

Advanced Intelligent Systems, EarlyView.
Commercial vertical NAND flash memory supports Bayesian neural networks by using paired cells to produce bell‐shaped weight distributions. Read voltage controls their spread without additional memory cells or changes to the array structure. Simulations based on device measurements demonstrate improved uncertainty estimation and accuracy gains of up to ...
Sung‐Ho Park, Mingyun Oh, Dongbeen Shin, Jaehyeon Kim, Jonghyun Ko, Jiseong Im, Yeongheon Yang, Gyuweon Jung, Jong‐Ho Lee   +8 more
wiley   +1 more source

Prosumers and Sustainable Market Governance: Development of the Community‐Oriented Marketing Approach Scale

Business Strategy and the Environment, EarlyView.
ABSTRACT This research develops and empirically validates the Community‐Oriented Marketing Approach (COMA), a 20‐item multidimensional scale designed to measure prosumer perceptions within participatory market systems. COMA conceptualizes prosumers as active co‐value creators and institutional agents, driving sustainable market governance.
Alpaslan Kelleci, Oguzhan Essiz
wiley   +1 more source

Do Banks in the Middle East and North Africa Region Price Carbon Exposure?

Business Strategy and the Environment, EarlyView.
ABSTRACT This study examines whether carbon exposure is incorporated into corporate borrowing costs within the Middle East and North Africa (MENA) region. Using a panel of 771 firm‐year observations from publicly listed non‐financial firms between 2016 and 2023, the analysis investigates the relationship between carbon intensity and firms' cost of debt
Yara Ibrahim, Khaled Hussainey, Taghred Mokhtar Sayed Moawad   +2 more
wiley   +1 more source

Design and Implementation of a Three-Layer Backpropagation Neural Network for Multi-Output Regression in Citizen-Science Impact Assessment

AI
Measuring the impact of citizen-science projects is hard because inputs are heterogeneous, mostly categorical, and sparse. We present Alquimics, a compact supervised neural network trained on one-hot project descriptors to predict impacts across five ...
Luigi Ceccaroni, Lyle Visa, Iain Visa
doaj   +1 more source