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

Explore cutting-edge developments in AI hardware architecture and In-Memory computing paradigms during this 72-minute technical talk presented by ST Microelectronics Fellow and Director Nitin Chawla. Dive into the complexities of novel hardware architectures specifically designed for resource-constrained devices, discovering how they enable efficient real-time inference of machine learning models at the edge. Examine practical real-world applications while learning how In-Memory Neural Processors optimize data movement and computation to boost edge AI system performance and energy efficiency without sacrificing reconfigurability. Gain valuable insights into scaling TinyML workloads and implementing advanced computing architectures for edge applications.