Search Results for author: Gary G. Yen

Found 23 papers, 4 papers with code

A Composite Decomposition Method for Large-Scale Global Optimization

no code implementations2 Mar 2024 Maojiang Tian, Minyang Chen, Wei Du, Yang Tang, Yaochu Jin, Gary G. Yen

Furthermore, to enhance the efficiency and accuracy of CSG, we introduce two innovative methods: a multiplicatively separable variable detection method and a non-separable variable grouping method.

Problem Decomposition Variable Detection

Diffusion Model-Based Multiobjective Optimization for Gasoline Blending Scheduling

no code implementations4 Feb 2024 Wenxuan Fang, Wei Du, Renchu He, Yang Tang, Yaochu Jin, Gary G. Yen

The presence of nonlinearity, integer constraints, and a large number of decision variables adds complexity to this problem, posing challenges for traditional and evolutionary algorithms.

Evolutionary Algorithms Multiobjective Optimization +1

Improving Performance Insensitivity of Large-scale Multiobjective Optimization via Monte Carlo Tree Search

no code implementations8 Apr 2023 Haokai Hong, Min Jiang, Gary G. Yen

In this work, we propose an evolutionary algorithm for solving LSMOPs based on Monte Carlo tree search, the so-called LMMOCTS, which aims to improve the performance and insensitivity for large-scale multiobjective optimization problems.

Multiobjective Optimization

Efficient Evaluation Methods for Neural Architecture Search: A Survey

no code implementations14 Jan 2023 Xiangning Xie, Xiaotian Song, Zeqiong Lv, Gary G. Yen, Weiping Ding, Yanan sun

In surveying each category, we further discuss the design principles and analyze the strength and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs.

Neural Architecture Search

Analyzing the Expected Hitting Time of Evolutionary Computation-based Neural Architecture Search Algorithms

no code implementations11 Oct 2022 Zeqiong Lv, Chao Qian, Gary G. Yen, Yanan sun

Evolutionary computation-based neural architecture search (ENAS) is a popular technique for automating architecture design of deep neural networks.

Neural Architecture Search

Learn to Adapt for Monocular Depth Estimation

no code implementations26 Mar 2022 Qiyu Sun, Gary G. Yen, Yang Tang, Chaoqiang Zhao

To boost the transferability of depth estimation models, we propose an adversarial depth estimation task and train the model in the pipeline of meta-learning.

Domain Adaptation Meta-Learning +1

BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search

1 code implementation9 Aug 2021 Xiangning Xie, Yuqiao Liu, Yanan sun, Gary G. Yen, Bing Xue, Mengjie Zhang

The paper conducts efficient comparison experiments on eight ENAS algorithms with high GPU utilization on this platform.

Benchmarking Neural Architecture Search

Snippet Policy Network for Multi-class Varied-length ECG Early Classification

no code implementations28 Jul 2021 Yu Huang, Gary G. Yen, Vincent S. Tseng

To the best of our knowledge, this is the first work focusing on solving the cardiovascular early classification problem based on varied-length ECG data.

Arrhythmia Detection Classification +4

System Design and Analysis for Energy-Efficient Passive UAV Radar Imaging System using Illuminators of Opportunity

no code implementations1 Oct 2020 Zhichao Sun, Junjie Wu, Gary G. Yen, Hang Ren, Hongyang An, Jianyu Yang

Then, a set of mission performance evaluators is established to quantitatively assess the capability of the system in a comprehensive manner, including UAV navigation, passive SAR imaging and communication.

Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency

no code implementations9 Apr 2020 Chaoqiang Zhao, Gary G. Yen, Qiyu Sun, Chongzhen Zhang, Yang Tang

This paper proposes a masked generative adversarial network (GAN) for unsupervised monocular depth and ego-motion estimation. The MaskNet and Boolean mask scheme are designed in this framework to eliminate the effects of occlusions and impacts of visual field changes on the reconstruction loss and adversarial loss, respectively.

Generative Adversarial Network Image Reconstruction +3

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

no code implementations29 Mar 2020 Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths

Then, we further review the performance of RL and meta-learning from the aspects of accuracy or transferability or both of them in autonomous systems, involving pedestrian tracking, robot navigation and robotic manipulation.

Deblurring Decision Making +12

ArcText: A Unified Text Approach to Describing Convolutional Neural Network Architectures

no code implementations16 Feb 2020 Yanan Sun, Ziyao Ren, Gary G. Yen, Bing Xue, Mengjie Zhang, Jiancheng Lv

Data mining on existing CNN can discover useful patterns and fundamental sub-comments from their architectures, providing researchers with strong prior knowledge to design proper CNN architectures when they have no expertise in CNNs.

Pruning Deep Convolutional Neural Networks Architectures with Evolution Strategy

no code implementations24 Dec 2019 Francisco Erivaldo Fernandes Junior, Gary G. Yen

Currently, Deep Convolutional Neural Networks (DCNNs) are used to solve all kinds of problems in the field of machine learning and artificial intelligence due to their learning and adaptation capabilities.

Automatically Evolving CNN Architectures Based on Blocks

no code implementations28 Oct 2018 Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen

The proposed algorithm is evaluated on CIFAR10 and CIFAR100 against 18 state-of-the-art peer competitors.

General Classification

Automatically designing CNN architectures using genetic algorithm for image classification

4 code implementations11 Aug 2018 Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen

Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years.

Classification General Classification +1

Improved Regularity Model-based EDA for Many-objective Optimization

no code implementations24 Feb 2018 Yanan Sun, Gary G. Yen, Zhang Yi

Finally, by assigning the Pareto-optimal solutions to the uniformly distributed reference vectors, a set of solutions with excellent diversity and convergence is obtained.

Dimensionality Reduction Evolutionary Algorithms

IGD Indicator-based Evolutionary Algorithm for Many-objective Optimization Problems

no code implementations24 Feb 2018 Yanan Sun, Gary G. Yen, Zhang Yi

Inverted Generational Distance (IGD) has been widely considered as a reliable performance indicator to concurrently quantify the convergence and diversity of multi- and many-objective evolutionary algorithms.

Evolutionary Algorithms

Evolving Unsupervised Deep Neural Networks for Learning Meaningful Representations

no code implementations13 Dec 2017 Yanan Sun, Gary G. Yen, Zhang Yi

Specifically, error classification rate on MNIST with $1. 15\%$ is reached by the proposed algorithm consistently, which is a very promising result against state-of-the-art unsupervised DL algorithms.

Evolutionary Algorithms General Classification

A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification

1 code implementation13 Dec 2017 Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen

Convolutional auto-encoders have shown their remarkable performance in stacking to deep convolutional neural networks for classifying image data during past several years.

General Classification Image Classification

Evolving Deep Convolutional Neural Networks for Image Classification

1 code implementation30 Oct 2017 Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen

Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights.

Classification General Classification +1

Transfer Learning based Dynamic Multiobjective Optimization Algorithms

no code implementations19 Dec 2016 Min Jiang, Zhongqiang Huang, Liming Qiu, Wenzhen Huang, Gary G. Yen

This approach takes the transfer learning method as a tool to help reuse the past experience for speeding up the evolutionary process, and at the same time, any population based multiobjective algorithms can benefit from this integration without any extensive modifications.

BIG-bench Machine Learning Multiobjective Optimization +1

Cannot find the paper you are looking for? You can Submit a new open access paper.