Guest Editors
Dr. Dilbag Singh
Email: dggill2@gmail.com
Affiliation: New York University, New York, 10016, USA
Homepage:
Research Interests:Deep learning, Machine learning, Multimodal learning, Novel Loss functions
Dr. Vijay Kumar
Email: vijayk@nitj.ac.in
Affiliation: NIT Jalandhar, Jalandhar, 43001, India.
Homepage:
Research Interests: Deep learning, Metaheuristics, Optimization
Dr. Manjit Kaur
Email: manjit.kaur@sru.edu.in
Affiliation: SR University, Warangal, 506371, India
Homepage:
Research Interests: Deep learning, Metaheuristics, Information security
Summary
The rapid evolution of artificial intelligence (AI) has led to the development of multimodal deep learning models that can process and integrate data from diverse sources such as text, images, audio, and videos. These multimodal deep learning models offer superior performance for various applications. However, there is a growing demand for deploying these models in real-world environments. These environments often involve resource constraints, such as limited processing power, memory, and energy, especially on edge devices like smartphones, wearables, and the Internet of Things (IoT). Combining multiple data modalities increases computational complexity, which can hinder deployment in real-world scenarios. Therefore, it is necessary to design optimized multimodal deep learning models by efficiently selecting either the architecture, hyperparameters, or both.
The aim of this special issue is to highlight the need for scalability and efficiency in multimodal deep learning models without compromising performance. Overall, this special issue aims to showcase the latest research and advancements in scalable and efficient multimodal deep learning models that can be deployed on lightweight devices for real-world applications. We seek contributions that address the challenges of developing models that can be deployed at scale, with a focus on reducing computational complexity, memory usage, and energy consumption while maintaining high performance. This issue will bring together innovative approaches that make these models practical and effective for a wide range of applications.
Topics of Interest:
We invite original research papers and case studies on various topics including, but not limited to:
· Scalable Architectures for Multimodal Deep Learning
· Lightweight Multimodal Deep Learning Model Design for Edge and IoT Devices
· Model Compression Techniques
· Efficient Training Strategies for Multimodal Deep Learning
· Multimodal Data Fusion Techniques
· Automated Model Optimization (AutoML) for Multimodal Learning
· Real-Time Multimodal Processing
· Benchmarking and Evaluation of Multimodal Deep Learning
· Security and Privacy in Multimodal Models
· Case Studies in Real-World Deployments
Keywords
Deep learning, Machine learning, Multimodal learning, Novel Loss functions
Login
Register
Submit a Paper
Propose a Special lssue