Methods for Creating Efficient Convolutional Neural Networks

Tuesday, May 21, 1:00 PM - 1:30 PM
Summit Track: 
Technical Insights I
Mission City B1-B5

In the past few years convolutional neural networks (CNN) have revolutionized several application domains in AI and computer vision. The biggest challenge with state-of-the-art CNNs is the massive compute demands that prevent these models from being used in many embedded systems and other resource-constrained environments. In this talk, I will explain and contrast several recent techniques that enable CNN models with high accuracy to consume very little memory and processor resources. These methods include a variety of algorithmic and optimization approaches to deep learning models. Quantization, sparsification and compact model design are three of the major techniques for efficient CNNs which will be discussed in the context of computer vision applications including detection, recognition and segmentation.


Mohammad Rastegari


Mohammad Rastegari is the cofounder and CTO of He is also a research scientist at AI2. His main area of research relies on the intersection of Computer Vision and Machine Learning. Previously, he was a Facebook Fellow, a visiting scholar at UC Berkeley and a PhD candidate at University of Maryland. Mohammad received his Bachelor's Degree from Shomal University of Amol, and his Master's Degree from University of Science and Research in Tehran where he was also a member of the computer vision lab at the Institute for Research in Fundamental Science.

See you at the Summit! May 20-23 in Santa Clara, California!
Register today and reserve your hotel room!