Dhaval Patel, Giridhar Ganapavarapu, et al.
AAAI 2022
In the deep-learning community, new algorithms are published at a very fast pace. Therefore, solving an image classification problem for new datasets becomes a challenging task, as it requires to re-evaluate published algorithms and their different configurations in order to find a close to optimal classifier. To facilitate this process, before biasing our decision toward a class of neural networks or running an expensive search over the network space, we propose to estimate the classification difficulty of the dataset. Our method computes a single number that characterizes the dataset difficulty 97 × faster than training state-of-the-art networks. The proposed method can be used in combination with network topology and hyper-parameter search optimizers to efficiently drive the search toward promising neural network configurations.
Dhaval Patel, Giridhar Ganapavarapu, et al.
AAAI 2022
Dzung Phan, Vinicius Lima
INFORMS 2023
Amir Hossein Ashouri, Giovanni Mariani, et al.
ACM TACO
Dzung Phan, Pavankumar Murali, et al.
INFORMS 2022