Search Results - "backpropagation algorithms"

AI Deep Learning Optimization for Compact Dual-Polarized High-Isolation Antenna Using Backpropagation Algorithm by Wu, Duo-Long, Hu, Xiao Jian, Chen, Jin Hao, Ye, Liang Hua, Li, Jian-Feng

“…An artificial intelligence deep learning algorithm is proposed to analyze a dual-polarized high-isolation antenna effectively. The method is a building model…”
Get full text

Learning in Memristive Neural Network Architectures Using Analog Backpropagation Circuits by Krestinskaya, Olga, Salama, Khaled Nabil, James, Alex Pappachen

“…The on-chip implementation of learning algorithms would speed up the training of neural networks in crossbar arrays. The circuit level design and…”
Get full text

Evolutionary Neural Network model for West Texas Intermediate crude oil price prediction by Chiroma, Haruna, Abdulkareem, Sameem, Herawan, Tutut

“…•We propose approach for the prediction of the WTI crude oil price.•The values predicted by the proposed method and actual once are statistically equal.•The…”
Get full text

An Improved Prediction Algorithm for Noise of Transformer Considering Material Parameter Uncertainty by Yang, Fan, Xia, Yisha, Wang, Jiawei, Wang, Pengbo, Jiang, Hui

“…This study proposes a rapid transformer noise prediction method to quantify the propagation of electrical steel material uncertainties in transformer systems…”
Get full text

The Symplectic Adjoint Method: Memory-Efficient Backpropagation of Neural-Network-Based Differential Equations by Matsubara, Takashi, Miyatake, Yuto, Yaguchi, Takaharu

“…The combination of neural networks and numerical integration can provide highly accurate models of continuous-time dynamical systems and probabilistic…”
Get full text

Towards Accurate One-Stage Object Detection With AP-Loss by Chen, Kean, Li, Jianguo, Lin, Weiyao, See, John, Wang, Ji, Duan, Lingyu, Chen, Zhibo, He, Changwei, Zou, Junni

“…One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme…”
Get full text

Low-Complexity Fiber Nonlinearity Compensation Based on Operator Learning Over 12 075 km Single Model Fiber by He, Xingchen, Yan, Lianshan, Jiang, Lin, Yi, Anlin, Yu, Youren, Pu, Zhengyu, Pan, Wei, Luo, Bin

“…Fiber nonlinearity is a significant constraint on the maximum achievable capacity in long-distance fiber optic transmission systems. The fiber nonlinearity…”
Get full text

DeepBlue: Advanced convolutional neural network applications for ocean remote sensing by Wang, Haoyu, Li, Xiaofeng

“…In the last 40 years, remote sensing technology has evolved, significantly advancing ocean observation and catapulting its data into the big data era. How to…”
Get full text

Non-Parallel Voice Conversion Using Variational Autoencoders Conditioned by Phonetic Posteriorgrams and D-Vectors by Saito, Yuki, Ijima, Yusuke, Nishida, Kyosuke, Takamichi, Shinnosuke

“…This paper proposes novel frameworks for non-parallel voice conversion (VC) using variational autoencoders (VAEs). Although conventional VAE-based VC models…”
Get full text

Improved Computation for Levenberg-Marquardt Training by Wilamowski, Bogdan M, Hao Yu

“…The improved computation presented in this paper is aimed to optimize the neural networks learning process using Levenberg-Marquardt (LM) algorithm…”
Get full text

Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning by Guorui Feng, Guang-Bin Huang, Qingping Lin, Gay, R.

“…One of the open problems in neural network research is how to automatically determine network architectures for given applications. In this brief, we propose a…”
Get full text

Training Lightweight Deep Convolutional Neural Networks Using Bag-of-Features Pooling by Passalis, Nikolaos, Tefas, Anastasios

“…Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs…”
Get full text

An Integrated Deep Learning-Based Data Fusion and Degradation Modeling Method for Improving Prognostics by Wang, Di, Liu, Kaibo

“…Accurate prognostics are crucially important to prevent unexpected failures in industrial and service systems. This process aims to monitor the degradation…”
Get full text

Supervised Learning in Neural Networks: Feedback-Network-Free Implementation and Biological Plausibility by Lin, Feng

“…The well-known backpropagation learning algorithm is probably the most popular learning algorithm in artificial neural networks. It has been widely used in…”
Get full text

Multilabel Neural Networks with Applications to Functional Genomics and Text Categorization by ZHANG, Min-Ling, ZHOU, Zhi-Hua

“…In multilabel learning, each instance in the training set is associated with a set of labels and the task is to output a label set whose size is unknown a…”
Get full text

Training Photonic Mach Zehnder Meshes for Neural Network Acceleration by Wolff, Andy, Karanth, Avinash

“…Photonic neural networks enable faster and energy-efficient inferences for deep neural network implementations when compared to electrical counterparts. Prior…”
Get full text

Why RELU Units Sometimes Die: Analysis of Single-Unit Error Backpropagation in Neural Networks by Douglas, Scott C., Yu, Jiutian

“…Recently, neural networks in machine learning use rectified linear units (ReLUs) in early processing layers for better performance. Training these structures…”
Get full text

Comparison of Hospital Building’s Energy Consumption Prediction Using Artificial Neural Networks, ANFIS, and LSTM Network by Panagiotou, Dimitrios K., Dounis, Anastasios I.

“…Since accurate load forecasting plays an important role in the improvisation of buildings and as described in EU’s “Green Deal”, financial resources saved…”
Get full text

Mitigation of Fiber Nonlinearity Using a Digital Coherent Receiver by Millar, D S, Makovejs, S, Behrens, C, Hellerbrand, S, Killey, R I, Bayvel, P, Savory, S J

“…Coherent detection with receiver-based DSP has recently enabled the mitigation of fiber nonlinear effects. We investigate the performance benefits available…”
Get full text

Accelerating convolutional neural network training using ProMoD backpropagation algorithm by Gürhanlı, Ahmet

“…Convolutional neural networks (CNNs) play an important role in image recognition applications. Fast training of image recognition systems is a crucial point,…”
Get full text