Search

Your search keyword '"Gonsalves, Tad"' showing total 150 results
Start Over Author "Gonsalves, Tad"
150 results on '"Gonsalves, Tad"'

1. Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks

Author

Inoue, Sho and Gonsalves, Tad

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Unpaired image-to-image translation using Generative Adversarial Networks (GAN) is successful in converting images among multiple domains. Moreover, recent studies have shown a way to diversify the outputs of the generator. However, since there are no restrictions on how the generator diversifies the results, it is likely to translate some unexpected features. In this paper, we propose Style-Restricted GAN (SRGAN) to demonstrate the importance of controlling the encoded features used in style diversifying process. More specifically, instead of KL divergence loss, we adopt three new losses to restrict the distribution of the encoded features: batch KL divergence loss, correlation loss, and histogram imitation loss. Further, the encoder is pre-trained with classification tasks before being used in translation process. The study reports quantitative as well as qualitative results with Precision, Recall, Density, and Coverage. The proposed three losses lead to the enhancement of the level of diversity compared to the conventional KL loss. In particular, SRGAN is found to be successful in translating with higher diversity and without changing the class-unrelated features in the CelebA face dataset. To conclude, the importance of the encoded features being well-regulated was proven with two experiments. Our implementation is available at https://github.com/shinshoji01/Style-Restricted_GAN., Comment: 20 pages, 11 figures, 6 tables; Our implementation is available at https://github.com/shinshoji01/Style-Restricted_GAN

Published
2021

2. Facial Conditional Translation Using Multi-CartoonGAN with Central Biasing Instance Normalization

Author

Komatsu, Rina, Gonsalves, Tad, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Takama, Yasufumi, editor, Matsumura, Naohiro, editor, Yada, Katsutoshi, editor, Matsushita, Mitsunori, editor, Katagami, Daisuke, editor, Abe, Akinori, editor, Kashima, Hisashi, editor, Hiraoka, Toshihiro, editor, Uchiya, Takahiro, editor, and Rzepka, Rafal, editor

Published
2022
Full Text
View/download PDF

3. A Hybrid Approach for Metaheuristic Algorithms Using Island Model

Author

Li, Jiawei, Gonsalves, Tad, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, and Arai, Kohei, editor

Published
2022
Full Text
View/download PDF

20. List of contributors

Author

Balas, Valentina E., primary, Barhanpurkar, Kanishk, additional, Biswas, Swagatam, additional, Chandan, Swet, additional, Das, Arshavee, additional, Das, Indrani, additional, Das, Sanjoy, additional, Ghosh, Ankush, additional, Gonsalves, Tad, additional, Jabin, Suraiya, additional, Khan, Pritam, additional, Kumar, Sudhir, additional, Mandal, Sampurna, additional, Mishra, Sarthak, additional, Mones, Sk Md Basharat, additional, Rajawat, Anand Singh, additional, Ranjan, Priyesh, additional, Rawat, Romil, additional, Shah, Jyoti, additional, Sharma, Pragya, additional, Shaw, Rabindra Nath, additional, Singh, Tarun Pratap, additional, and Upadhyay, Jaychand, additional

Published
2021
Full Text
View/download PDF

23. Neuroevolution untuk optimalisasi parameter jaringan saraf tiruan

Author

Purnomo, Hindriyanto Dwi, Gonsalves, Tad, Wahyono, Teguh, Saian, Pratyaksa Ocsa Nugraha, Purnomo, Hindriyanto Dwi, Gonsalves, Tad, Wahyono, Teguh, and Saian, Pratyaksa Ocsa Nugraha

Abstract

Artificial Neural Network is a supervised learning method for various classification problems. Artificial Neural Network uses training data to identify patterns in the data; therefore, training phase is crucial. During this stage, the network weight is adjusted so that they can recognize patterns in the data. In this research, a neuroevolution approach is proposed to optimize artificial neural network parameters (weight) Neuroevolution is a combination of evolutionary algorithms, including various metaheuristics algorithms, to optimize neural network parameters and configuration. In particular, this research implemented particle swarm optimization as the artificial neural network optimizer. The performance of the proposed model was compared to backpropagation, which uses gradient information to adjust the neural network parameter. There are five datasets used as the benchmark problems. The datasets are iris, wine, breast cancer, ecoli, and wheat seeds. The experiment results show that the proposed method has better accuracy than the backpropagation in three out of five problems and has the same accuracy in two problems. The proposed method is also faster than the backpropagation method in all problems. These results reveal that neuroevolution is a promising approach to improving the performance of artificial neural networks. Further studies are needed to explore more benefits of this approach., Jaringan saraf tiruan merupakan metode supervised learning yang telah diterapkan untuk menyelesaikan berbagai permasalahan klasifikasi. Sebagai metode supervised learning, jaringan saraf tiruan memerlukan data training untuk mengidentifikasi pola dalam data sehingga fase learning menjadi penting. Pada fase learning, konfigurasi bobot pada jaringan saraf tiruan diatur sehingga jaringan saraf tiruan tersebut bisa mengenali pola di dalam data. Pada penelitian ini diusulkan metode untuk mengoptimalkan nilai bobot pada konfigurasi jaringan saraf tiruan menggunakan pendekatan neuroevolution. Neuroevolution adalah pengintegrasian metode evolutionary algorithm; termasuk di dalamnya adalah berbagai metode metaheuristik; dengan jaringan saraf tiruan. Secara khusus, penelitian ini menggunakan metode particle swarm optimization untuk mengoptimalkan bobot pada jaringan saraf tiruan. Kinerja model yang diusulkan dibandingkan dengan metode backpropagation dengan stochastic gradient descent menggunakan lima dataset: iris, wine, breast cancer, ecoli, dan wheat seeds. Hasil eksperimen menunjukkan bahwa model yang diusulkan memiliki akurasi yang lebih baik di tiga dataset dari lima dataset dan memiliki kinerja yang sama di dua dataset. Hasil penelitian ini mengindikasikan bahwa pendekatan neuroevolution memiliki potensi sebagai metode optimalisasi parameter pada jaringan saraf tiruan. Penelitian ini bisa dikembangkan dengan mengidentifikasi karakteristik konvergensi dari pendekatan neuroevolution maupun menerapkan berbagai metode evolutionary algorithm untuk mengoptimalkan nilai bobot pada jaringan saraf tiruan.

Published
2023

24. Monocular vision guided deep reinforcement learning UAV systems with representation learning perception.

Author

Xue, Zhihan and Gonsalves, Tad

Abstract

In recent years, numerous studies have applied deep reinforcement learning (DRL) algorithms to vision-guided unmanned aerial systems. However, DRL is not good at training deep networks in an end-to-end manner due to data inefficiency and lack of direct supervision signals. This paper provides a visual information dimension reduction scheme with representation learning as the visual perception module, which reduces the dimensions of high-dimensional visual information and retains its features related to UAV navigation. Combining such state representation learning with the DRL model can effectively reduce the complexity of the neural network required by DRL. Based on this scheme, we design three motion control models with a monocular camera as the main sensor and train them to control UAVs for obstacle avoidance tasks in a simulated environment. Experiments show that all these models achieve high obstacle avoidance ability after a certain period of training. In addition, one of them also enables the monocular vision guidance system to avoid obstacles in the blind spot of side vision. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results