LMLuiz Henrique Mormille
Luiz Henrique Mormille
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Luiz Henrique Mormille has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Clifford Broni-Bediako
Soka University, Hachioji-shi, Japan
2 shared publicationsMasayasu Atsumi
Soka University, Hachioji-shi, Japan
2 shared publications- Clifford Broni-Bediako
RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
1 shared publication - Masayasu Atsumi
Graduate School of Science and Engineering Soka University Hachioji Tokyo Japan
1 shared publication Yuki Murata
Graduate School of Science and Engineering Soka University Hachioji Tokyo Japan
1 shared publication
Latest Publications
- 5 January 2023
- Published by Springer Nature in Artificial Life and Robotics
- Vol. 28 (1) , 106-116
Introducing inductive bias on vision transformers through Gram matrix similarity based regularization
- 5 January 2023
- Published by Springer Nature in Artificial Life and Robotics
- Vol. 28 (1) , 106-116
Introducing inductive bias on vision transformers through Gram matrix similarity based regularization
- 18 July 2022
- Published by Springer Nature in Artificial Life and Robotics
- Vol. 27 (3) , 586-593
Regularizing self-attention on vision transformers with 2D spatial distance loss
- 18 July 2022
- Published by Springer Nature in Artificial Life and Robotics
- Vol. 27 (3) , 586-593
Regularizing self-attention on vision transformers with 2D spatial distance loss
- Open Access
Evolutionary NAS with Gene Expression Programming of Cellular Encoding
The renaissance of neural architecture search (NAS) has seen classical methods such as genetic algorithms (GA) and genetic programming (GP) being exploited for convolutional neural network (CNN) architectures. While recent work have achieved promising performance on visual perception tasks, the direct encoding scheme of both GA and GP has functional complexity deficiency and does not scale well on large architectures like CNN. To address this, we present a new generative encoding scheme -- $symbolic\ linear\ generative\ encoding$ (SLGE) -- simple, yet powerful scheme which embeds local graph transformations in chromosomes of linear fixed-length string to develop CNN architectures of variant shapes and sizes via evolutionary process of gene expression programming. In experiments, the effectiveness of SLGE is shown in discovering architectures that improve the performance of the state-of-the-art handcrafted CNN architectures on CIFAR-10 and CIFAR-100 image classification tasks; and achieves a competitive classification error rate with the existing NAS methods using less GPU resources.Open AccessEvolutionary NAS with Gene Expression Programming of Cellular Encoding
The renaissance of neural architecture search (NAS) has seen classical methods such as genetic algorithms (GA) and genetic programming (GP) being exploited for convolutional neural network (CNN) architectures. While recent work have achieved promising performance on visual perception tasks, the direct encoding scheme of both GA and GP has functional complexity deficiency and does not scale well on large architectures like CNN. To address this, we present a new generative encoding scheme -- $symbolic\ linear\ generative\ encoding$ (SLGE) -- simple, yet powerful scheme which embeds local graph transformations in chromosomes of linear fixed-length string to develop CNN architectures of variant shapes and sizes via evolutionary process of gene expression programming. In experiments, the effectiveness of SLGE is shown in discovering architectures that improve the performance of the state-of-the-art handcrafted CNN architectures on CIFAR-10 and CIFAR-100 image classification tasks; and achieves a competitive classification error rate with the existing NAS methods using less GPU resources.