Bio:

Coby is the CEO of Weebit Nano. Coby has over 45 years’ of experience in the semiconductor and related industries, including engineering, engineering management, sales, and executive roles. Coby was previously CEO at PacketLight Networks, and held VP Worldwide Sales roles at both Verisity and Jasper Design Automation. Coby also set up his own consulting company, EDAcon Partners, helping startups define their corporate strategies, build their worldwide sales channels, and raise capital. Coby holds a Bachelor of Science in Systems Design from Technion – Israel Institute of Technology.

Abstract:

As AI workloads shift increasingly towards inference across cloud, edge, industrial, and connected systems, memory is becoming a central factor in determining performance, power efficiency, latency, and scalability. This evolution is driving a broader transition in memory architectures, as conventional approaches struggle with the growing cost and power related to data movement between compute and memory. This presentation examines how emerging non-volatile memory technologies such as ReRAM are enabling more efficient AI systems that achieve lower power operation, faster responsiveness, and advanced-node scalability. The session will also explore how these trends are shaping the longer-term evolution toward memory-centric AI architectures, including in-memory compute approaches designed to support the next generation of AI inference.