Fast gradient descent for multi-objective waveform design

2016 ◽  
Author(s):  
Brian O'Donnell ◽  
John Michael Baden
Keyword(s):  
Gradient Descent ◽  
Waveform Design ◽  
Multi Objective ◽  
Fast Gradient

scholarly journals Enhanced tensor factorization framework using non-negative and probabilistic tensor factorization approaches for microblogging content propagation modelling

2017 ◽  
Vol 7 (1.1) ◽  
pp. 88
Author(s):  
N. Baggyalakshmi ◽  
A. Kavitha ◽  
A. Marimuthu
Keyword(s):  
Gradient Descent ◽  
User Behavior ◽  
Complete System ◽  
Propagation Model ◽  
Tensor Factorization ◽  
Propagation Modeling ◽  
Factorization Model ◽  
Factorization Structure ◽  
Linguistic Patterns ◽  
Fast Gradient

With the aim of identifying the user’s preferences, Content propagation modeling from the micro-blogging sites aids diverse organizations. In existing studies, four user behavior aspects were used by the content propagation model that is to say topic virality, user’s position, user susceptibility and user virality. The propagation occurrences are signified as a tensor factorization model so-called V2S is presented with the aim of deriving the behavioral aspects via which the content propagation is designed. On the other hand, it doesn’t comprise the linguistic patterns in the content that decreases the performance of the content propagation. Moreover, by utilizing advanced tensor approaches, the factorization structure is improved. Therefore the performance of the complete system is decreased meaningfully. With the aim of overcoming the aforesaid problems, Enhanced V2S (EV2S) Tensor Factorization framework is presented in this research that make use of the Probabilistic Latent Tensor Factorization (PLTF) as well as Non-negative Tensor Factorization (NTF) in order to derive the behavioral facets. NTF is presented for decreasing the content propagation errors. By making use of fast gradient descent technique, the unrestrained issue, which happens in this model is solved. This research system identifies the reposts as well as re-tweets in huge datasets proficiently with minimum processing time. From the experimentation outcomes, it is proved that the EV2S-PLTF tensor factorization performs better when compared to the previous tensor frameworks.

scholarly journals Multi-Objective Defocus Robust Source and Mask Optimization Using Sensitive Penalty

2019 ◽  
Vol 9 (10) ◽  
pp. 2151
Author(s):  
Pengzhi Wei ◽  
Yanqiu Li ◽  
Tie Li ◽  
Naiyuan Sheng ◽  
Enze Li ◽  
...  
Keyword(s):  
Gradient Descent ◽  
Process Window ◽  
Sensitivity Factor ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Lithography Process ◽  
Wide Range ◽  
Focus Plane ◽  
Technology Nodes ◽  
First Time

The continuous decrease in the size of lithographic technology nodes has led to the development of source and mask optimization (SMO) and also to the control of defocus becoming stringent in the actual lithography process. Due to multi-factor impact, defocusing is always changeable and uncertain in the real exposure process. But conventional SMO assumes the lithography system is ideal, which only compensates the optical proximity effect (OPE) in the best focus plane. Therefore, to solve the inverse lithography problem with more uniformity of pattern in different defocus variations, we proposed a defocus robust SMO (DRSMO) approach that is driven by a defocus sensitivity penalty function for the first time. This multi-objective optimization samples a wide range of defocus disturbances and it can be proceeded by the mini-batch gradient descent (MBGD) algorithm effectively. The simulation results showed that a more robust defocus source and mask can be designed through DRSMO optimization. The defocus sensitivity factor sβ maximally decreased 63.5% compared to conventional SMO, and due to the low error sensitivity and the depth of defocus (DOF), the process window (PW) was further enlarged effectively. Compared to conventional SMO, the exposure latitude (EL) maximally increased from 4.5% to 10.5% and DOF maximally increased 54.5% (EL = 5%), which proved the validity of the DRSMO method in improving the focusing performance.

Modeling for Production Rate Measurement of Hydrocyanic Acid Based on PSONN

2012 ◽  
Vol 233 ◽  
pp. 409-415
Author(s):  
Zhong Jian Tang ◽  
Miao Song
Keyword(s):  
Production Rate ◽  
Gradient Descent ◽  
Pso Algorithm ◽  
Measurement Model ◽  
Descent Method ◽  
Hydrocyanic Acid ◽  
Gradient Descent Method ◽  
Production Engineering ◽  
Soft Measurement ◽  
Fast Gradient

Aimed at the problem that it is difficult to measure production rate of hydrocyanic acid directly. So the soft measurement model of production rate of hydrocyanic acid can be established based on neural networks according to interrelated measurable engineering signals. Before being application to engineering, the soft measurement model is trained by PSO algorithm instead of the fast gradient descent method; Simulations prove that the soft measurement model trained by PSO possesses better measuring accuracy and stronger generalization ability. This kind of soft measurement model can be applied to practical production engineering of hydrocyanic acid.

Fast gradient descent method for Mean-CVaR optimization

2013 ◽  
Vol 205 (1) ◽  
pp. 203-212 ◽  
Author(s):  
Garud Iyengar ◽  
Alfred Ka Chun Ma
Keyword(s):  
Gradient Descent ◽  
Descent Method ◽  
Gradient Descent Method ◽  
Fast Gradient

scholarly journals Boosting Adversarial Attacks on Neural Networks with Better Optimizer

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Heng Yin ◽  
Hengwei Zhang ◽  
Jindong Wang ◽  
Ruiyu Dou
Keyword(s):  
Neural Networks ◽  
Success Rate ◽  
Gradient Descent ◽  
State Of The Art ◽  
Black Box ◽  
Security Threats ◽  
Gradient Descent Algorithm ◽  
Gradient Based ◽  
Adversarial Examples ◽  
Fast Gradient

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence poses potential security threats to deep learning systems. Sophisticated adversarial examples with strong attack performance can also be used as a tool to evaluate the robustness of a model. However, the success rate of adversarial attacks can be further improved in black-box environments. Therefore, this study combines a modified Adam gradient descent algorithm with the iterative gradient-based attack method. The proposed Adam iterative fast gradient method is then used to improve the transferability of adversarial examples. Extensive experiments on ImageNet showed that the proposed method offers a higher attack success rate than existing iterative methods. By extending our method, we achieved a state-of-the-art attack success rate of 95.0% on defense models.

Sign in / Sign up

Export Citation Format

Share Document