March 24, 2023
March 24, 2023
Deep learning methods have made great strides in machine intelligence over the past few years, but they are now having trouble keeping up with the growing amount of data and resources. As traditional system architectures get closer to their physical limits, the problem of compute scalability is getting worse, which makes it hard to predict how far AI methods and systems can go in the future. These issues beg the question: What are alternative directions for the next-generation of AI methods and systems that will run them?
Processing domains like analog, asynchronous, event-based, probabilistic, neuromorphic, photonic, and quantum computing have all shown promise for faster, more efficient AI with new capabilities through a complete shift in the way AI systems work.
The goal of this workshop is to kick off discussions about next-generation systems and methods that will help AI move forward, specifically through a realistic assessment of how these exotic emerging approaches for next-generation AI are making progress toward practical relevance and in what timeframes.
We want to help both experts and non-experts, believers and doubters, by achieving the following goals:
- Educate about new processing technology and AI methods on the horizon.
- Evaluate the strengths and paths to practical viability of different approaches.
- Discuss methods to compare next-generation systems against traditional systems and against each other.
- Inspire the integration of new technologies toward future AI methods and systems.
SNAP Workshop Call for Papers
We encourage submissions from next-generation processing domains that have the potential to strongly outperform traditional AI system methods in terms of speed and efficiency or that can unlock new computational paradigms for AI. Areas of interest include analog, asynchronous, event-based, probabilistic, neuromorphic, photonic, and quantum computing, but they may not be the only ones. Submissions of early research and pre-printed work is encouraged.
Works that survey, compare, or integrate next-gen processing systems are highly encouraged. Specific contributed paper themes include:
- Domain survey papers describing research trends and future outlooks and challenges.
- Assessments of practical viability and technological timeframes for next-gen processing.
- Evaluation methods for comparing next-generation AI systems, both internally and externally to their domain.
- Benchmark results for next-gen AI systems against traditional systems.
- Application-specific systems highlighting next-gen technology domain strengths.
- Integrations of next-gen processing with traditional computing systems.
- Programming frameworks or computing abstractions for next-gen algorithms.
Submissions should be at most four pages long.
Submission Deadline: March 24, 2023
Author Notification: April 30, 2023
Workshop Date: June 8, 2023
Vijay Janapa Reddi, Harvard
Charlotte Frenkel, TU Delft
Brian Anderson, Intel
Jason Yik, Harvard
Zergham Ahmed, Harvard