Edge AI and TinyML: Revolutionizing Real-Time Intelligence in Resource-Constrained Devices
Abstract
Edge AI and TinyML are redefining how intelligence is deployed on low-power, resource-constrained devices. This paper reviews recent advancements in deploying machine learning models directly on edge devices, reducing latency and enhancing privacy. It explores model compression techniques, hardware accelerators, and optimized inference engines. The study highlights applications in wearable devices, industrial IoT, and environmental monitoring. Challenges such as limited computational capacity, energy efficiency, and model accuracy trade-offs are critically analyzed. The paper concludes with future directions in neuromorphic computing and decentralized AI architectures.
References
Singh, B., Anand, A., Prabhat, S., & Ranjan, P. (2025). Threat Onboarding and Response (TOR): Automating Cybersecurity in Enterprise Networks.
Anand, A., Singh, B., & Prabhat, S. (2022). Real-Time Network Monitoring and Incident Response with AI-Driven Automation Data Center and WAN Transformation. Available at SSRN 5577033.
Anand, A., Singh, B., Khemka, S., Banerjee, B., Bhatia, V. S., & Ranjan, P. (2025, October). Malware Classification using Diluted Convolutional Neural Network with Fast Gradient Sign Method. In 2025 2nd International Conference on Software, Systems and Information Technology (SSITCON) (pp. 1-5). IEEE.
Singh, B., Bhatia, V., Anand, A., Edamadaka, G., & Sudhakar, M. (2025, June). Intent-based Software Defined Networking for Flexible Network Management in Heterogeneous Environments. In 4th Conference on SGCNSP-2025.
Cherukuri, R., Yarram, V. K., Parimi, S. K., & Jegajothi, B. (2025, November). Leveraging ML for Enhanced User Experience in Web Applications. In 2025 5th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS) (pp. 757-764). IEEE.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning foundations and trends. MIT Press Journal.
Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255–260.
