COMPLEX DATA CLUSTERING WITH SINGLE-LAYER DYNAMICALLY LINKED SPIKING NEURAL NETWORK by A.A. KRASNOSHCHEKOV

“…The method allows to apply single-layered spiking neural networks that encode each data dimension by one neuron of the input layer for the recognition of complex and overlapping clusters with procedure of unsupervised training. …”
Get full text

Stabilizing training of affine coupling layers for high-dimensional variational inference by Daniel Andrade

Get full text

DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User Interactions by Joannes Sam Mertens, Salvatore Cafiso, Laura Galluccio, Giacomo Morabito, Giuseppina Pappalardo

“…Therefore, this work proposes a novel training technique called Sequential Training that partitions the Neural Network (NN) layers of the DNN model into two sets of layers that are trained so that one is specific of the user while the other is trained cooperatively to be specific of the road environment. …”
Get full text

Efficacy of Smart City Data Layers in virtual reality for emergency evacuation behaviours by Reinout Wiltenburg, William Hurst, Frida Ruiz Mendoza, Caspar Krampe, Bedir Tekinerdogan

“…One way of presenting this information is by employing the Smart City Data Layers which has yet to be investigated, thus, in this study, a Smart City Data Layer-enhanced virtual reality environment is presented. …”
Get full text

Deep representation learning using layer-wise VICReg losses by Joy Datta, Rawhatur Rabbi, Puja Saha, Aniqua Nusrat Zereen, M. Abdullah-Al-Wadud, Jia Uddin

“…Abstract This paper presents a layer-wise training procedure of neural networks by minimizing a Variance-Invariance-Covariance Regularization (VICReg) loss at each layer. …”
Get full text

RGB Color Space-Enhanced Training Data Generation for Cucumber Classification by Hotaka Hoshino, Takuya Shindo, Takefumi Hiraguri, Nobuhiko Itoh

“…In this paper, we propose a method for embedding information related to cucumber length, bend, and thickness into the background space of cucumber images when creating training data. Specifically, this method encodes these attributes into the RGB color space, allowing the background color to vary based on the cucumber’s length, bend, and thickness. …”
Get full text

A Robust Enhanced Ensemble Learning Method for Breast Cancer Data Diagnosis on Imbalanced Data by Zhenzhen Wang, Junde Xie, Jia Zhang

Get full text

Analysis and training of a traffic sign recognition neural network model by A. U. Mentsiev, T. G. Aigumov, E. M. Abdulmukminova

“…Deep learning methods were used, namely convolutional neural networks, which allow you to automatically extract image characteristics and train on a large data set. The research methodology included the following steps: collecting and preparing a variety of road sign data, creating and training a neural network model based on convolutional layers, applying data augmentation methods to improve model performance, and evaluating the model’s effectiveness on a test data set.Result. …”
Get full text

Double-layer stacking optimization for electricity theft detection considering data incompleteness and intra-class imbalance by Leijiao Ge, Jingjing Li, Tianshuo Du, Luyang Hou

“…To address these issues, this paper presents a method utilizing a two-stage time-series generative adversarial network (TimeGAN) with an integrated two-layer stacking optimization configuration. The first phase tackles data incompleteness through an enhanced version of TimeGAN, employing embedding and recovery layers to reconstruct incomplete power user data. …”
Get full text

Enhancing Cognitive Workload Classification Using Integrated LSTM Layers and CNNs for fNIRS Data Analysis by Mehshan Ahmed Khan, Houshyar Asadi, Mohammad Reza Chalak Qazani, Adetokunbo Arogbonlo, Siamak Pedrammehr, Adnan Anwar, Hailing Zhou, Lei Wei, Asim Bhatti, Sam Oladazimi, Burhan Khan, Saeid Nahavandi

“…However, conventional machine learning methods, although simpler to implement, undergo a complex pre-processing phase before network training and demonstrate reduced accuracy due to inadequate data preprocessing. …”
Get full text

Switch test method of train communication network based on Ethernet by YANG Peng

“…By analyzing the application requirements of train control and diagnosis based on train communication network topology and Ethernet, and concluding the services to be provided by ETB and ECN switches, a function and performance test method for ETB switch and ECN switch was raised, which could cover the physical layer, data link layer, the network layer, the transport layer and the application layer. …”
Get full text

A multi-layered defense against adversarial attacks in brain tumor classification using ensemble adversarial training and feature squeezing by Ahmeed Yinusa, Misa Faezipour

“…We then applied a multi-layered defense strategy, including adversarial training with FGSM and PGD examples and feature squeezing techniques such as bit-depth reduction and Gaussian blurring. …”
Get full text

Superiority of Combined Endurance-Resistance Exercise for Increasing the Molecular and Pyramidal Layers Thickness of Hippocampal Tissue in Alzheimer\'s Laboratory Large White Rats by Maryam Keshvari, Ali Heidarianpour, Farzaneh Chehelcheraghi

“…Introduction: The thickness of the molecular and pyramidal layers in the hippocampus represents a pivotal aspect of Alzheimer's research. …”
Get full text

Manual Segmentation of 12 Layers of the Retina and Choroid through SD-OCT in Intermediate AMD: Repeatability and Reproducibility by Pedro Camacho, Marco Dutra-Medeiros, Luís Salgueiro, Sílvia Sadio, Paulo C. Rosa

Get full text

Optimization of dual-layer flow field in a water electrolyzer using a data-driven surrogate model by Lizhen Wu, Zhefei Pan, Shu Yuan, Xiaoyu Huo, Qiang Zheng, Xiaohui Yan, Liang An

“…Therefore, machine learning methods are adopted to accelerate the optimization. A data-driven surrogate model based on deep neural network (DNN) is developed and successfully trained using data obtained by the physical VOF method. …”
Get full text

Efficient Ransomware Detection in Resource-Constrained Environments Using Optimized Multi-Layer Perceptron Networks by Tuxiang Lin, Rongliang Lin

Get full text

Design and Implementation of Fault Diagnosis and Data Synchronization Scheme Based on Train Redundant Display Platform by TIAN Deqiang, JIANG Xuezhai, ZHANG Xiaofeng, ZHANG Guangqiang, LIAO Jifang

“…The display platform of train provides the train driver with the key data of the running train and receives control command input. …”
Get full text

Training of the feed-forward artificial neural networks using butterfly optimization algorithm by Şaban Gülcü, Büşra Irmak

“…Researchers have proposed algorithms to train Multi-Layer Perceptron (MLP). However, classical techniques often face problems in solving this optimization problem. …”
Get full text

A complete, multi-layered quranic treebank dataset with hybrid syntactic annotations for classical arabic processingMendeley Data by Wadee A. Nashir, Abdulqader M. Mohsen, Asma A. Al-Shargabi, Mohamed K. Nour, Badriyya B. Al-onazi

“…EQTB offers significant reuse potential, providing crucial training/evaluation data for diverse CA NLP tasks (parsing, morphology, diacritization), supporting linguistic research, and enabling the development of advanced pedagogical tools and language technologies.…”
Get full text

Small sample smart contract vulnerability detection method based on multi-layer feature fusion by Jinlin Fan, Yaqiong He, Huaiguang Wu

“…Therefore, to overcome the challenges posed by limited smart contract vulnerability datasets and high false positive rates, we introduce a data augmentation technique that incorporates function feature screening with those special smart contracts into the training set. …”
Get full text