Z
Zhichao Lu
Researcher at Southern University of Science and Technology
Publications - 40
Citations - 1033
Zhichao Lu is an academic researcher from Southern University of Science and Technology. The author has contributed to research in topics: Computer science & Evolutionary algorithm. The author has an hindex of 9, co-authored 31 publications receiving 451 citations. Previous affiliations of Zhichao Lu include Michigan State University.
Papers
More filters
Proceedings ArticleDOI
NSGA-Net: neural architecture search using multi-objective genetic algorithm
Zhichao Lu,Ian Whalen,Vishnu Naresh Boddeti,Yashesh Dhebar,Kalyanmoy Deb,Erik D. Goodman,Wolfgang Banzhaf +6 more
TL;DR: Experimental results suggest that combining the dual objectives of minimizing an error metric and computational complexity, as measured by FLOPs, allows NSGA-Net to find competitive neural architectures.
Journal ArticleDOI
Neural Architecture Transfer
Zhichao Lu,Gautam Sreekumar,Erik D. Goodman,Wolfgang Banzhaf,Kalyanmoy Deb,Vishnu Naresh Boddeti +5 more
TL;DR: Experimental evaluation indicates that, across diverse image classification tasks and computational objectives, NAT is an appreciably more effective alternative to conventional transfer learning of fine-tuning weights of an existing network architecture learned on standard datasets.
Proceedings ArticleDOI
Multiview Transformers for Video Recognition
TL;DR: This work presents Multiview Transformers for Video Recognition (MTV), a model that consists of separate encoders to represent different views of the input video with lateral connections to fuse information across views and achieves state-of-the-art results on six standard datasets.
Journal ArticleDOI
Multiobjective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
Zhichao Lu,Ian Whalen,Yashesh Dhebar,Kalyanmoy Deb,Erik D. Goodman,Wolfgang Banzhaf,Vishnu Naresh Boddeti +6 more
TL;DR: In this paper, an evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating point operations (FLOPs), is proposed, which improves computational efficiency by carefully down-scaling the architectures during the search and reinforcing the patterns commonly shared among past successful architectures through Bayesian model learning.
Posted Content
NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search.
Zhichao Lu,Ian Whalen,Vishnu Naresh Boddeti,Yashesh D. Dhebar,Kalyanmoy Deb,Erik D. Goodman,Wolfgang Banzhaf +6 more
TL;DR: Experimental results suggest that combining the objectives of minimizing both an error metric and computational complexity, as measured by FLOPS, allows NSGA-Net to find competitive neural architectures near the Pareto front of both objectives on two different tasks, object classification and object alignment.