Sangeeta Sinha
Sangeeta Sinha is a technology professional and researcher with expertise in DevOps, performance engineering, artificial intelligence, and emerging digital ecosystems. With a strong background in cloud computing and modern application testing, she focuses on designing secure, scalable, and trustworthy systems. She has presented at national and international forums on AI, blockchain, and performance testing, and actively contributes to advancing responsible innovation in computer science.
Sangeeta is deeply passionate about the transformative potential of cloud computing and its role in shaping the future of technology. She believes the cloud is not just an infrastructure platform but a powerful enabler of innovation, resilience, and democratized access to intelligence. From accelerating AI adoption to empowering global collaboration, she envisions the cloud as a foundation for trustworthy, ethical, and scalable digital ecosystems. Her work explores how cloud possibilities—combined with AI, security, and governance—can unlock sustainable growth and human-centered innovation in an increasingly connected world.
Sessions
In a network of connected devices, there are two critical aspects of the system to succeed:
Security – with a number of internet-connected devices, securing the network from cyber threats is very important. Privacy - The devices capture business sensitive data that the Organisation has to safeguard to maintain their differentiation. I've used Federated learning to build anomaly detection models that monitor data quality and cybersecurity – while preserving data privacy.
Federated learning enables Edge devices to collaboratively learn deep learning models but keeping all of the data on the device itself. Instead of moving data to the cloud, the models are trained on the device and only the updates of the model are shared across the network.
Using federated learning gave me the following advantages:
Ability to build more accurate models faster Low latency during inference Privacy-preserving Improved energy efficiency of the devices I built deep learning models using tensorflow and deployed using uTensor. uTensor is a light-weight ML inference framework built on Mbed and Tensorflow.
In this talk, I will discuss in detail on how I built federated learning models on the edge devices.