scholarly journals Optimal learning group formation: A multi-objective heuristic search strategy for enhancing inter-group homogeneity and intra-group heterogeneity

2019 ◽  
Vol 118 ◽  
pp. 506-521 ◽  
Author(s):  
Soheila Garshasbi ◽  
Yousef Mohammadi ◽  
Sabine Graf ◽  
Samira Garshasbi ◽  
Jun Shen
Keyword(s):  
Heuristic Search ◽  
Search Strategy ◽  
Group Formation ◽  
Optimal Learning ◽  
Multi Objective ◽  
Learning Group ◽  
Group Heterogeneity ◽  
Group Homogeneity

EVOLUTIONARY MULTI-OBJECTIVE OPTIMISATION OF NEURAL NETWORKS FOR FACE DETECTION

2004 ◽  
Vol 04 (03) ◽  
pp. 237-253 ◽  
Author(s):  
STEFAN WIEGAND ◽  
CHRISTIAN IGEL ◽  
UWE HANDMANN
Keyword(s):  
Search Strategy ◽  
Human Face ◽  
Video Streams ◽  
Feed Forward Neural Network ◽  
Image Region ◽  
Multi Objective ◽  
Strategy Adaptation ◽  
Gradient Based ◽  
Speed And Accuracy ◽  
Single Objective

For face recognition from video streams speed and accuracy are vital aspects. The first decision whether a preprocessed image region represents a human face or not is often made by a feed-forward neural network (NN), e.g. in the Viisage-FaceFINDER® video surveillance system. We describe the optimisation of such a NN by a hybrid algorithm combining evolutionary multi-objective optimisation (EMO) and gradient-based learning. The evolved solutions perform considerably faster than an expert-designed architecture without loss of accuracy. We compare an EMO and a single objective approach, both with online search strategy adaptation. It turns out that EMO is preferable to the single objective approach in several respects.

scholarly journals Front-to-Front Heuristic Search for Satisficing Classical Planning

2020 ◽  
Author(s):  
Ryo Kuroiwa ◽  
Alex Fukunaga
Keyword(s):  
Heuristic Search ◽  
Search Strategy ◽  
State Of The Art ◽  
Heuristic Evaluation ◽  
Bidirectional Search

Although symbolic bidirectional search is successful in optimal classical planning, state-of-the-art satisficing planners do not use bidirectional search. Previous bidirectional search planners for satisficing planning behaved similarly to a trivial portfolio, which independently executes forward and backward search without the desired ``meet-in-the-middle'' behavior of bidirectional search where the forward and backward search frontiers intersect at some point relatively far from the forward and backward start states. In this paper, we propose Top-to-Top Bidirectional Search (TTBS), a new bidirectional search strategy with front-to-front heuristic evaluation. We show that TTBS strongly exhibits ``meet-in-the-middle'' behavior and can solve instances solved by neither forward nor backward search on a number of domains.

scholarly journals Heuristic Search Strategy for Transforming Microstructural Patterns to Optimal Copolymerization Recipes

2018 ◽  
Vol 27 (2) ◽  
pp. 1700088 ◽  
Author(s):  
Yousef Mohammadi ◽  
Mohammad Reza Saeb ◽  
Alexander Penlidis
Keyword(s):  
Heuristic Search ◽  
Search Strategy

scholarly journals An Empirical Study of Meta- and Hyper-Heuristic Search for Multi-Objective Release Planning

2018 ◽  
Vol 27 (1) ◽  
pp. 1-32 ◽  
Author(s):  
Yuanyuan Zhang ◽  
Mark Harman ◽  
Gabriela Ochoa ◽  
Guenther Ruhe ◽  
Sjaak Brinkkemper
Keyword(s):  
Empirical Study ◽  
Heuristic Search ◽  
Release Planning ◽  
Multi Objective
Sign in / Sign up

Export Citation Format

Share Document