no code implementations • 20 Feb 2024 • Ehsan Rokhsatyazdi, Shahryar Rahnamayan, Sevil Zanjani Miyandoab, Azam Asilian Bidgoli, H. R. Tizhoosh
Finding the optimal values for weights of ANNs is a large-scale optimization problem.
no code implementations • 20 Feb 2024 • Sevil Zanjani Miyandoab, Shahryar Rahnamayan, Azam Asilian Bidgoli
In this regard, we define feature selection as a multi-objective binary optimization task with the objectives of maximizing classification accuracy and minimizing the number of selected features.
no code implementations • 20 Feb 2024 • Sevil Zanjani Miyandoab, Shahryar Rahnamayan, Azam Asilian Bidgoli
For this purpose, we have proposed the binary multi-objective coordinate search (MOCS) algorithm to solve large-scale feature selection problems.
no code implementations • 15 Apr 2023 • Pooria Mazaheri, Azam Asilian Bidgoli, Shahryar Rahnamayan, H. R. Tizhoosh
By forcing the model to learn the ranking of matched outputs, the representation learning is customized toward image search instead of learning a class label.
no code implementations • 2 Mar 2023 • Azam Asilian Bidgoli, Shahryar Rahnamayan, Taher Dehkharghanian, Abtin Riasatian, H. R. Tizhoosh
Coarse multi-objective feature selection uses the reduced search space strategy guided by the classification accuracy and the number of features.
1 code implementation • journal 2022 • Majid Seydgar, Shahryar Rahnamayan, Pedram Ghamisi, Azam Asilian Bidgoli
The generated pseudo labels of our proposed framework can be fed to various DNNs to improve their generalization capacity.
Ranked #1 on Semi-Supervised Image Classification on Salinas (using extra training data)
no code implementations • 24 Jul 2020 • Kyle Robert Harrison, Azam Asilian Bidgoli, Shahryar Rahnamayan, Kalyanmoy Deb
In the context of optimization, visualization techniques can be useful for understanding the behaviour of optimization algorithms and can even provide a means to facilitate human interaction with an optimizer.