Title: On Entrepreneurship, Academia, and Deep Learning
Date: June 04, 2025, Wednesday
Time: 12:30 – 14:30
Location: 1003, Mayer Building, Technion
Abstract:
This talk will begin by describing a few foundational elements of deep learning along with elementary concepts in neural network inference optimization to provide context for understanding the work and innovations at Deci AI, a neural network design and optimization startup that was acquired by NVIDIA in 2024. Following this light technical discussion, we’ll tell the story of building Deci, sharing practical lessons from the startup journey including both successes and challenges encountered along the way, and touch on the relationship between academic research and entrepreneurship in the AI field.
Speaker Bio:
Ran El-Yaniv is a Professor of Computer Science at the Technion (currently on leave) and Senior Director at NVIDIA where he leads the Deci research team following NVIDIA’s 2024 acquisition
of Deci AI, which he co-founded. The Deci team at NVIDIA focuses on building efficient large language models and contributed significantly to the design and creation of one of the currently leading open-source LLMs, recently released, working alongside other teams at NVIDIA. El-Yaniv holds a PhD in Computer Science from the University of Toronto and completed postdoctoral work at MIT and the Hebrew University. His academic research focuses on selective prediction and uncertainty estimation, computational creativity, financial modeling, and AI including large language models. He coauthored the textbook “Online Computation and Competitive Analysis” (Cambridge University Press) and received the 2016 Yanai Prize for Excellence in Academic Education at the Technion.