A review on weight initialization strategies for neural networks

MV Narkhede, PP Bartakke, MS Sutaone - Artificial intelligence review, 2022 - Springer
Over the past few years, neural networks have exhibited remarkable results for various
applications in machine learning and computer vision. Weight initialization is a significant …

Backpropagation neural networks modelling of photocatalytic degradation of organic pollutants using TiO2‐based photocatalysts

BV Ayodele, MA Alsaffar, SI Mustapa… - Journal of Chemical …, 2020 - Wiley Online Library
BACKGROUND The advanced oxidation process using photocatalysts has been proven to
be an efficient technique used for the degradation of organic pollutants in wastewater …

Synchronous multi-stream hidden markov model for offline Arabic handwriting recognition without explicit segmentation

K Jayech, MA Mahjoub, NEB Amara - Neurocomputing, 2016 - Elsevier
Arabic handwriting recognition is still a challenging task due especially to the unlimited
variation in human handwriting, the large variety of Arabic character shapes, the presence of …

Spiking pattern recognition using informative signal of image and unsupervised biologically plausible learning

S Nazari - Neurocomputing, 2019 - Elsevier
The recent progress of low-power neuromorphic hardware provides exceptional conditions
for applications where their focus is more on saving power. However, the design of spiking …

Neural-Network-Based Model for Trailing-Edge Flap Loads in Preliminary Aircraft Design

R Stephan, C Heyen, E Stumpf, J Ruhland… - Journal of Aircraft, 2024 - arc.aiaa.org
Accurately predicting the forces and moments acting on trailing-edge devices under different
flight conditions is a critical aspect in the design of the kinematics and actuation for high-lift …

A generalized Lorenz system-based initialization method for deep neural networks

B Jia, Z Guo, T Huang, F Guo, H Wu - Applied Soft Computing, 2024 - Elsevier
Deep neural networks (DNNs) are a powerful tool for solving complex problems. The
effectiveness of DNNs largely depends on the initialization technique used. This research …

Hearing loss detection in medical multimedia data by discrete wavelet packet entropy and single-hidden layer neural network trained by adaptive learning-rate back …

S Wang, S Du, Y Li, H Lu, M Yang, B Liu… - Advances in Neural …, 2017 - Springer
In order to develop an efficient computer-aided diagnosis system for detecting left-sided and
right-sided sensorineural hearing loss, we used artificial intelligence in this study. First, 49 …

Isomorphic model-based initialization for convolutional neural networks

H Zhang, Y Li, H Yang, B He, Y Zhang - Journal of Visual Communication …, 2022 - Elsevier
Modern deep convolutional neural networks (CNNs) are often designed to be scalable,
leading to the model family concept. A model family is a large (possibly infinite) collection of …

WSNs self-calibration approach for smart city applications leveraging incremental machine learning techniques

R Rossini, E Ferrera, D Conzon… - 2016 8th IFIP …, 2016 - ieeexplore.ieee.org
The diffusion of the Internet of Things paradigm, in the last few years, has led to the need of
deploying and managing large-scale Wireless Sensor Networks (WSNs), composed by a …

[图书][B] Deep Learning Applied to Animal Linguistics

C Bergler - 2023 - search.proquest.com
Even nowadays, people have only a very limited understanding about animal
communication. Scientists are still far from identifying statistically relevant, animal-specific …