EMC^2 2018 - 2018 Workshop On Energy Efficient Machine Learning And Cognitive Computing For Embedded Applications

A new wave of intelligent computing, driven by recent advances in machine learning and cognitive algorithms coupled with process technology and new design methodologies, has the potential to usher unprecedented disruption in the way conventional computing solutions are designed and deployed. These new and innovative approaches often provide an attractive and efficient alternative not only in terms of performance but also power, energy, and area.
A key class of these intelligent solutions is providing real-time, on-device cognition at the edge to enable many novel applications including vision and image processing, language translation, autonomous driving, malware detection, and gesture recognition. Naturally, these applications have diverse requirements for performance, energy, reliability, accuracy, and security that demand a holistic approach to designing the hardware, software, and intelligence algorithms to achieve the best power, performance, and area (PPA).
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 embedded 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.
LIST OF POTENTIAL IDEAS
Computing techniques for IoT, Automotive, and mobile intelligence
Exploration new and efficient applications of machine learning
Machine learning benchmarks, workloads and their characterization
Performance and bottleneck analysis, profiling and synthesis of workloads
Simulation and emulation techniques, frameworks and platforms for neural networks
Energy efficient techniques and solutions for neural networks
Communication and computation overlapping and load balancing techniques
Efficient hardware proposals to implement neural networks
Power and performance efficient memory architectures
Exploring the interplay between precision, performance, power and energy
Approximation, quantization and reduced precision computing techniques
Power, Performance and Area (PPA) based comparison of neural networks
Exploration of new areas, domains and applications where machine learning can be applied efficiently
Efficient learning techniques -- supervised vs unsupervised
Improvements over conventional training techniques
Inference vs Training comparison and analysis in terms of power, performance and complexity
Hardware/software techniques to exploit sparsity and locality
Support vector machines (SVM) based solutions
Systolic array based architectures and systems for machine learning applications
Security and privacy challenges and building secure systems