DAC-ROAD4NN 2023 Workshop Call for Paper and Demo

4th ROAD4NN Workshop: Research Open Automatic Design for Neural Networks

Co-located with the 60th Design Automation Conference (DAC 2023)

Jul 9th, 2023. Moscone Center West, San Francisco, CA, USA

https://sites.google.com/view/road4nn 

 

In the past decade, machine learning, especially neural network based deep learning, has achieved amazing success. Various types of neural networks, such as CNNs, RNNs, LSTMs, BERTs, GNNs, SNNs, and the recent vision transformers and ChatGPT, have been deployed for various industrial applications like image classification, speech recognition, natural language understanding, autonomous driving, and automated control. On one hand, there is a very fast algorithm evolvement of neural network models. Almost every week there is a new model from a major academic and/or industry institute. On the other hand, all major industry giants have been developing and/or deploying specialized hardware platforms to accelerate the performance and improve the energy-efficiency of neural networks across the cloud and edge devices. This includes Nvidia GPUs, Google TPUs, ARM and Qualcomm mobile CPUs and GPUs, programmable DSPs and NPUs, Intel Nervana/Habana/Loihi ASICs, AMD/Xilinx and Intel FPGAs, Microsoft Brainwave, Amazon Inferentia, to name just a few. However, there is a significant gap between the fast algorithm evolvement and staggering hardware development, hence calling for broader participation in software-hardware co-design from both academia and industry. 

In this workshop, we focus on the open research of automated design for neural networks, a holistic open-source approach to general-purpose computer systems broadly inspired by neural networks. More specifically, we discuss full stack open-source infrastructure support to develop and deploy novel neural networks, including novel algorithms and applications, hardware architectures and emerging digital/analog devices, as well as programming, compiler, system, and tool support. We plan to bring together academic and industry experts to share their experience, discuss challenges they face as well as potential focus areas for the community.

We are soliciting work-in-progress papers and live demos from the community. Workshop topics include, but are not limited to:

·       Application of neural networks in new areas, e.g., autonomous driving, climate, agriculture

·       Advancements of neural network algorithms

·       Bio-plausible neural network models

·       Neural network model compression, quantization, and network architecture search

·       Hardware acceleration and architecture for neural networks

·       New circuits and devices for neural networks

·       Abstraction to bridge the algorithm and hardware gap for neural networks

·       Compilation and design automation support to map neural networks to hardware platforms

·       System support to deploy neural networks in cloud and edge devices

·       Benchmarks for various neural network models and hardware accelerators

·       Other research infrastructures that enable the above studies

Submission guidelines:

Interested authors are encouraged to submit their work-in-progress papers (up to four pages) through HotCRP (link: https://dac-road4nn2023.hotcrp.com). Authors are encouraged to submit preliminary work for new projects and early results. The paper selection will follow a double-blind review process. Manuscripts should not exceed 4 single-spaced, double-column pages using 10-point size font on 8.5×11 inch pages (ACM sigconf conference style: http://www.acm.org/publications/proceedings-template), including references, figures, and tables. All papers must be submitted electronically in PDF format. Accepted papers will be invited to give a 25-min talk with a 5-min Q/A each. There will be NO proceedings, so that authors can still submit their papers to other conferences/journals. The deadline for submission is Apr 24th, 11:59 PM (Pacific Time), 2023.

This year, authors are also encouraged to submit live demos to showcase their cool projects; the demos can be based on either published or unpublished work. Demos will be selected with a single-blind review process. Similarly, a demo description that does not exceed 4 pages following the same ACM sigconf conference style should be submitted electronically in PDF format. Accepted demos will be invited to showcase in the workshop live demo session. There will be NO proceedings. The deadline for the live demo submission is also Apr 24th, 11:59 PM (Pacific Time), 2023.

For this year, all accepted papers and demos are expected to present in person.

Student presentation and demo awards:

We will select three Best Student Presentations and three Best Student Demos from the workshop.

·       For each Best Student Presentation, we will provide USD $500 student travel grant.

·       For Best Student Demos, we will provide USD $1,000, $500, and $200 cash prize for the first, second, and third place winner, respectively.

Important dates:

·       Paper and demo submission: Apr 24th, 2023, 11:59 PM (Pacific Time)

·       Author notification: May 8th, 2023 (Pacific Time)

·       Workshop date: Jul 9th, 2023 (Pacific Time)

Organizers:

·       Zhenman Fang, Simon Fraser University, Canada (zhenman@sfu.ca)

·       Yanzhi Wang, Northeastern University, US (yanz.wang@northeastern.edu)

·       Linghao Song, UCLA, USA (linghaosong@cs.ucla.edu)

 

 

DAC-ROAD4NN 2023 Workshop Call for Paper and Demo