This talk will describe methods to enable energy-efficient processing for deep learning, specifically convolutional neural networks (CNN), which is the cornerstone of many deep-learning algorithms. Deep learning plays a critical role in extracting meaningful information out of the zetabytes of sensor data collected every day. For some applications, the goal is to analyze and understand the data to identify trends (e.g., surveillance, portable/wearable electronics); in other applications, the goal is to take immediate action based the data (e.g., robotics/drones, self-driving cars, smart Internet of Things). For many of these applications, local embedded processing near the sensor is preferred over the cloud due to privacy or latency concerns, or limitations in the communication bandwidth. However, at the sensor there are often stringent constraints on energy consumption and cost in addition to throughput and accuracy requirements. Furthermore, flexibility is often required such that the processing can be adapted for different applications or environments (e.g., update the weights and model in the classifier). We will give a short overview of the key concepts in CNNs, discuss its challenges particularly in the embedded space, and highlight various opportunities that can help to address these challenges at various levels of design ranging from architecture, implementation-friendly algorithms, and advanced technologies (including memories and sensors).
Slides: www.rle.mit.edu/eems/wp-conten...
Paper: www.rle.mit.edu/eems/wp-conten...
Professional Education Course: professional-education.mit.edu...