tinyML Talks: Empowering the Edge: Advancements in AI Hardware and In-Memory Computing Architectures

Empowering the Edge: Advancements in AI Hardware and In-Memory Computing Architectures for TinyML

Nitin Chawla
Fellow and Director
ST Microelectronics

This talk will cover AI hardware architecture and In-Memory computing paradigms tailored for Edge applications with scalability towards TinyML workloads. We will look at the intricacies of novel hardware architectures optimized for resource-constrained devices, enabling efficient and real-time inference of machine learning models. We will look at real-world examples to discover how In-Memory Neural Processors further manage data movement and computation to enhance edge AI systems’ performance and energy efficiency while maintaining reconfigurability.

source