Workshop on Energy Efficient Machine Learning and Cognitive Computing

announcement Important Announcements

Call for Proposal announced for EMC2 6th Edition: To make the EMC2 Workshop more accessible to the community, we are transitioning to a virtual format this year. 6th Edition will be an independent virtual event on December 5, 2020. For further details and logistics, please look out our Call for Proposal and keep checking our website

EMC2 Model Compression Challenge: We are pleased to announce the first EMC2 Model Compression Challenge (EMCC) which aims to identify the best ideas and approaches for deep learning model compression. Check this page for more details.

memory Upcoming Workshops

schedule Program for EMC2 at EMC2 Virtual Workshop 2020

09:00 - 10:00
Energy Efficient Machine Learning on Encrypted Data: Hardware to the Rescue
Farinaz Koushanfar, University of California, San Diego
10:00 - 10:40
DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
Wojciech Samek, Fraunhofer Heinrich Hertz Institute
10:40 - 11:20
Efficient Machine Learning via Data Summarization
Baharan Mirzasoleiman, Computer Science, University of California, Los Angeles
11:20 - 12:00
Modular Neural Networks for Low-Power Image Classification on Embedded Devices
Yung-Hsiang Lu, Purdue University
13:00 - 13:40
Techniques for Efficient Inference with Deep Networks
Raghu Krishnamoorthi, Facebook
13:40 - 14:20
Designing Nanosecond Inference Engines for the Particle Collider
Clauidonor N. Coelho Jr, (Palo Alto Networks) Thea Aarrestad (CERN) Vladimir Loncar (CERN) Maurizio Pierini (CERN) Adrian Alan Pol (CERN) Sioni Summers (CERN), Palo Alto Networks, CERN
14:20 - 15:00
Efficient Deep Learning At Scale
Hai Li, Duke Univesity
View the complete program for the 6th Edition of EMC2 here.

description Workshop Objective

As artificial intelligence and other forms of cognitive computing continue to proliferate into new domains, many forums for dialogue and knowledge sharing have emerged. In the proposed workshop, the primary focus is on the exploration of energy efficient techniques and architectures for cognitive computing and machine learning, particularly for applications and systems running at the edge. For such resource constrained environments, performance alone is never sufficient, requiring system designers to carefully balance performance with power, energy, and area (overall PPA metric).

The goal of this workshop is to provide a forum for researchers who are exploring novel ideas in the field of energy efficient machine learning and artificial intelligence for a variety of applications. We also hope to provide a solid platform for forging relationships and exchange of ideas between the industry and the academic world through discussions and active collaborations.

format_list_bulleted Topics for the Workshop

  • Architectures for the edge: IoT, automotive, and mobile
  • Approximation, quantization reduced precision computing
  • Hardware/software techniques for sparsity
  • Neural network architectures for resource constrained devices
  • Neural network pruning, tuning and and automatic architecture search
  • Novel memory architectures for machine learing
  • Communication/computation scheduling for better performance and energy
  • Load balancing and efficient task distribution techniques
  • Exploring the interplay between precision, performance, power and energy
  • Exploration of new and efficient applications for machine learning
  • Characterization of machine learning benchmarks and workloads
  • Performance profiling and synthesis of workloads
  • Simulation and emulation techniques, frameworks and platforms for machine learning
  • Power, performance and area (PPA) based comparison of neural networks
  • Verification, validation and determinism in neural networks
  • Efficient on-device learning techniques
  • Security, safety and privacy challenges and building secure AI systems

Recent Editions

View the complete list of previous editions.