Embedded Files
Dr. Arjun Ghosh
Doctorate (PhD) in Computer Science and Engineering, National Institute of Technology Durgapur, West Bengal, India.
Research interests include Artificial Intelligence, AutoML, Deep Learning, Neural Architecture Search (NAS), Computer Vision, and Evolutionary Computation.
B.Sc (Honours) in Computer Science, M.Sc in Computer Science, and M.Tech in Computer Science and Engineering.
Email: rjun.cse@gmail.com, ag18cs1108@phd.nitdgp.ac.in
Arjun Ghosh completed his doctoral degree in 2024 from the Department of Computer Science and Engineering at the National Institute of Technology Durgapur, India. His research extensively explores Artificial Intelligence, particularly Deep Learning (DL). His work primarily focuses on developing novel algorithms for automatically designing optimal deep neural networks in computer vision tasks using evolutionary algorithms. Deep learning (DL) models, particularly convolutional neural networks (CNNs), excel in computer vision tasks, but optimizing their architecture remains challenging. Neural architecture search (NAS) automates DL model design specifically for computer vision tasks. Collaborations with various sectors offer opportunities to expand this work to GAN-based image generation, LSTM-based predictions, and federated learning, driving efficiency and innovation across sectors.
Prior to his PhD studies, he earned his master's degree (M.Tech) in Computer Science and Engineering (CSE) from the Maulana Abul Kalam Azad University of Technology (Formerly known as the West Bengal University of Technology), India. He also holds an M.Sc in Computer Science (CS) from North Bengal University, India. He graduated with honours from Malda College of North Bengal University, India, with a bachelor's degree in computer science. He is an active member of the Institute of Electrical and Electronics Engineers (IEEE) in India and has served as a reviewer for multiple journals and conferences.
Recent Activities:
[Patent] Indian Industrial Design Patent “CNN ARCHITECTURE OPTIMIZATION DEVICE” under Intellectual Property Right, Govt of India (Application Number- 404796-001, C.B.R number- 200786, 17/01/2024), Certificate of Design Generated, Journal No is 15/2024 and Journal Date is 12/04/2024.
[Journal] Arjun Ghosh, Nanda Dulal Jana, Swagatam Das and Rammohan Mallipeddi,“Two-Phase Evolutionary Convolutional Neural Network Architecture Search for Medical Image Classification,” IEEE Access, vol. 11, pp. 115280-115305, 2023.[pdf]
[Conference] Arjun Ghosh and Nanda Dulal Jana. "Artificial bee colony optimization based optimal convolutional neural network architecture design". In 2022 IEEE 19th India Council InternationalConference (INDICON), pages 1-7, IEEE, 2022 [pdf].
[Book Chapter] Sandipan Dhar, Arjun Ghosh, Swarup Roy, Avirup Mazumder, and Nanda Dulal Jana. " Hyper-parameter Optimization of CNN using Genetic Algorithm for Speech Command Recognition", Book Chapter in Advances in Data-driven Computing and Intelligent Systems. Lecture Notes in Networks and Systems, Volume 2, Springer, 2023, pp. 123–135, isbn: 2367-3389. [pdf]
[Journal] Arjun Ghosh, Nanda Dulal Jana, Saurav Mallik, and Zhongming Zhao. "Designing optimal convolutional neural network architecture using differential evolution algorithm". Patterns, Elsevier, volume 3, page 100567, 2022 [pdf].
[Poster] Arjun Ghosh and Nanda Dulal Jana presented a poster on " An Overview of Neural Architecture Search for Image Classification Problems" at Research Scholar Day at the National Institute of Technology Durgapur, India.
Page updated
Google Sites
Report abuse