Results 111 to 120 of about 127,617 (265)

Backpropagation-Friendly Eigendecomposition

, 2019
Eigendecomposition (ED) is widely used in deep networks. However, the backpropagation of its results tends to be numerically unstable, whether using ED directly or approximating it with the Power Iteration method, particularly when dealing with large matrices.
Wang, Wei, Dang, Zheng, Hu, Yinlin, Fua, Pascal, Salzmann, Mathieu   +4 more
openaire   +2 more sources

Solving Data Overlapping Problem Using A Class‐Separable Extreme Learning Machine Auto‐Encoder

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
The overlapping and imbalanced data in classification present key challenges. Class‐separable extreme learning machine auto‐encoding (CS‐ELM‐AE) is proposed, which is an enhancement of ELM‐AE that better handles overlapping data by clustering points from the same class together. Applying oversampling addresses imbalanced data.
Ekkarat Boonchieng, Wanchaloem Nadda
wiley   +1 more source

Visual Backpropagation

, 2019
We show how a declarative functional programming specification of backpropagation yields a visual and transparent implementation within spreadsheets. We call our method Visual Backpropagation. This backpropagation implementation exploits array worksheet formulas, manual calculation, and has a sequential order of computation similar to the processing of
openaire   +2 more sources

Predicting Performance of Hall Effect Ion Source Using Machine Learning

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
This study introduces HallNN, a machine learning tool for predicting Hall effect ion source performance using a neural network ensemble trained on data generated from numerical simulations. HallNN provides faster and more accurate predictions than numerical methods and traditional scaling laws, making it valuable for designing and optimizing Hall ...
Jaehong Park, Guentae Doh, Dongho Lee, Youngho Kim, Changmin Shin, Su‐Jin Shin, Young‐Chul Ghim, Sanghoo Park, Wonho Choe   +8 more
wiley   +1 more source

Investigation of Analog Memristor Characteristics for Hardware Synaptic Weight in Multilayer Neural Network

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
The systematic design of memristor‐based neural network is provided by analog conductance state parameters to accurately emulate the software‐based high‐resolution weight at discrete device level. The requirement of discrete analog conductance of memristor device is measured as ≈50 states with nonlinearity value of ≈0.142 within the deviation range of ...
Jingon Jang, Yoonseok Song, Sungjun Park
wiley   +1 more source

Seeing Through the Face: Robust Facial Diagnosis Enhanced by Landmark Detection and Pose Normalization

Advanced Intelligent Systems, EarlyView.
This study proposes a robust, generalizable new approach for facial type diagnosis. Based on landmark detection and pose normalization, a 94.7% diagnostic accuracy is achieved by Combined Heatmap Regression and Coordinate Regression network. This research makes the AI‐generated preliminary diagnosis more interpretable and reducing the impact of ...
Qianyang Xie, Zixian Jiao, Guo Bai, Huimin Zhu, Dahe Zhang, Hui Li, Haixia Lu, Xin Nie, Qing Li, Duohong Zou, Zhiguo Yin, Peilun Li, Chi Yang   +12 more
wiley   +1 more source

Robust Implicit Backpropagation

, 2018
Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate. The sensitivity to the learning rate is due to the reliance on backpropagation to train the network. In this paper we present the first application of Implicit Stochastic Gradient Descent (ISGD) to train neural networks, a method ...
Fagan, Francois, Iyengar, Garud
openaire   +2 more sources

Roadmap on Artificial Intelligence‐Augmented Additive Manufacturing

Advanced Intelligent Systems, EarlyView.
This Roadmap outlines the transformative role of artificial intelligence‐augmented additive manufacturing, highlighting advances in design, monitoring, and product development. By integrating tools such as generative design, computer vision, digital twins, and closed‐loop control, it presents pathways toward smart, scalable, and autonomous additive ...
Ali Zolfagharian, Liuchao Jin, Qi Ge, Wei‐Hsin Liao, Andrés Díaz Lantada, Francisco Franco Martínez, Tianyu Zhang, Tao Liu, Charlie C. L. Wang, Mohammad Hossein Mosallanejad, Reza Ghanavati, Abdollah Saboori, Alejandro De Blas De Miguel, William Solórzano‐Requejo, Yi Cai, Xiangyang Dong, Huangyi Qu, Najmeh Samadiani, Guangyan Huang, Austin Downey, Yanzhou Fu, Lang Yuan, Tsz‐Kwan (Glory) Lee, Arbind Agrahari Baniya, Eisha Waseem, Abdul Rahman Sani, Abbas Z. Kouzani, Yijia Wu, Markus P. Nemitz, Masoud Shirzad, Dageon Oh, Seung Yun Nam, Amedeo Franco Bonatti, Irene Chiesa, Gabriele Maria Fortunato, Giovanni Vozzi, Carmelo De Maria, Mahdi Bodaghi   +37 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

Device‐Level Implementation of Reservoir Computing With Memristors

Advanced Intelligent Systems, EarlyView.
Reservoir computing (RC) is an emerging computing scheme that employs a reservoir and a single readout layer, which can be actualized in the nanoscale with memristors. As a comprehensive overview, the principles of RC and the switching mechanisms of memristors are discussed, followed by actual demonstrations of memristor‐based RC and the remaining ...
Sunbeom Park, Hyojung Kim, Ho Won Jang
wiley   +1 more source