Workshop on Bridging the Gap between Artificial to Natural Intelligence

Despite tremendous progress in recent deep learning algorithms and hardware, there still exists three to four orders of energy efficiency gap between artificial and natural intelligence. Towards bringing this gap, up-to-date results of neuroscience needs to be abstracted to the algorithmic level, so that they can be implemented in engineering solutions. Based on understanding how the brain works, engineers from various disciplines need to collaborate on learning algorithms, knowledge representation, and architectures. The objective of this workshop is to bring together researchers from across the JUMP (Joint University Microelectronics Program, funded by SRC and DARPA) community to discuss the most promising approaches towards the overarching goal of bridging the energy efficiency gap between artificial and natural intelligence. The workshop will explicitly focus on approaches that are well beyond today’s deep neural networks and neural network accelerators. Topics of interest will include bio-inspired network models and learning algorithms, neuro-mimetic devices and circuits, and hardware that embodies the information processing principles of the brain. Exemplary research efforts from both academia and industry will be presented. The workshop aims to establish a forum to discuss the current practices, as well as future research needs in the corresponding fields.

Organizers

Jae-sun Seo (Arizona State University)

Arijit Raychowdhury (Georgia Institute of Technology)

Logistics

• Date & time: June 2 (Sunday), 2019, 8:30AM - 4:30PM
• Venue: Las Vegas Convention Center (Map)
• Room: N259

Workshop Agenda

8:30 AM Introduction and opening remarks

Session 1: Bio-Plausible Algorithms (Session Chair: Priyadarshini Panda, Yale University)

8:45 AM Kaushik Roy (Purdue University): Deep Spiking Neural Networks: Opportunities and Challenges

9:00 AM Dan Hammerstrom (Portland State University): What Exactly is Bio-Inspired Machine Learning?

9:15 AM Laurent Itti (University of Southern California): Bio-Inspired Algorithms for Continual Learning

9:30 AM Yu Cao (Arizona State University): Continual Learning for a Dynamic System

9:45 AM Discussion with Session 1 speakers

10:15 AM Coffee break

Session 2: Brain-Inspired Architectures (Session Chair: Vijaykrishnan Narayanan, Penn State University)

10:30 AM Anand Raghunathan (Purdue University): Crossbar Based AI Hardware Architecture

10:45 AM Tajana Rosing (University of California San Diego): Hyperdimensional Computing and Its Applications

11:00 AM Gu-Yeon Wei (Harvard University): Optimizing On-Chip Non-Volatile Storage for Visual Multi-Task Inference at the Edge

11:15 AM Discussion with Session 2 speakers

11:45 AM Lunch

Session 3: Bio-Plausible Circuits and Devices (Session Chair: Vivek De, Intel Labs)

1:15 PM Jae-sun Seo (Arizona State University): SRAM-based In-memory Computing Fabrics for Neuromorphic Computing

1:30 PM Shimeng Yu (Georgia Institue of Technology): In-memory Computing based on RRAM Technologies

1:45 PM Suman Datta (University of Notre Dame): Role of Emerging Electronics in Machine Learning and Neuromorphic Computing

2:00 PM Discussion with Session 3 speakers

2:30 PM Coffee break

Session 4: Industry Perspective (Session Chair: Jae-sun Seo, Arizona State University)

2:45 PM Manish Pandey (Synopsys): Near-Memory and Extreme Data Reduction for Energy-Efficient Neural Networks

3:00 PM Titash Rakshit (Samsung Semiconductor, Inc.): Bridging the Energy Gap: Can electronics catch up to the Brain?

3:15 PM Pritish Narayanan (IBM Almaden Research Center): Even-More-Neuromorphic Computing - Can Hardware Play a Role?

3:30 PM Discussion with Session 4 speakers

4:00 PM Conclusion of Workshop