no code implementations • 31 Oct 2024 • Tianyi Zhang, Baoxin Li, Jae-sun Seo, Yu Cao
In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks.
no code implementations • 10 Oct 2024 • Yiwei Zhao, Ziyun Li, Win-San Khwa, Xiaoyu Sun, Sai Qian Zhang, Syed Shakib Sarwar, Kleber Hugo Stangherlin, Yi-Lun Lu, Jorge Tomas Gomez, Jae-sun Seo, Phillip B. Gibbons, Barbara De Salvo, Chiao Liu
We also introduce H4H-NAS, a Neural Architecture Search framework to design efficient hybrid CNN/ViT models for heterogeneous edge systems with both NPU and CIM.
1 code implementation • 8 Sep 2024 • Yuzong Chen, Jian Meng, Jae-sun Seo, Mohamed S. Abdelfattah
On the hardware side, we demonstrate the potential of BBS through BitVert, a bitserial architecture with an efficient PE design to accelerate DNNs with low overhead, exploiting our proposed binary pruning.
1 code implementation • 2 May 2024 • Jian Meng, Yuan Liao, Anupreetham Anupreetham, Ahmed Hasssan, Shixing Yu, Han-sok Suh, Xiaofeng Hu, Jae-sun Seo
The limited degree of freedom in the current toolkit and the under-explored customization hinder the prototype ASIC or FPGA-based accelerator design.
1 code implementation • 10 Dec 2023 • Tianyi Zhang, Kishore Kasichainula, Yaoxin Zhuo, Baoxin Li, Jae-sun Seo, Yu Cao
Conventional super-resolution methods suffer from two drawbacks: substantial computational cost in upscaling an entire large image, and the introduction of extraneous or potentially detrimental information for downstream computer vision tasks during the refinement of the background.
1 code implementation • 3 Nov 2023 • Tianyi Zhang, Kishore Kasichainula, Yaoxin Zhuo, Baoxin Li, Jae-sun Seo, Yu Cao
Early object detection (OD) is a crucial task for the safety of many dynamic systems.
1 code implementation • 10 Apr 2023 • Jason Yik, Korneel Van den Berghe, Douwe den Blanken, Younes Bouhadjar, Maxime Fabre, Paul Hueber, Weijie Ke, Mina A Khoei, Denis Kleyko, Noah Pacik-Nelson, Alessandro Pierro, Philipp Stratmann, Pao-Sheng Vincent Sun, Guangzhi Tang, Shenqi Wang, Biyan Zhou, Soikat Hasan Ahmed, George Vathakkattil Joseph, Benedetto Leto, Aurora Micheli, Anurag Kumar Mishra, Gregor Lenz, Tao Sun, Zergham Ahmed, Mahmoud Akl, Brian Anderson, Andreas G. Andreou, Chiara Bartolozzi, Arindam Basu, Petrut Bogdan, Sander Bohte, Sonia Buckley, Gert Cauwenberghs, Elisabetta Chicca, Federico Corradi, Guido de Croon, Andreea Danielescu, Anurag Daram, Mike Davies, Yigit Demirag, Jason Eshraghian, Tobias Fischer, Jeremy Forest, Vittorio Fra, Steve Furber, P. Michael Furlong, William Gilpin, Aditya Gilra, Hector A. Gonzalez, Giacomo Indiveri, Siddharth Joshi, Vedant Karia, Lyes Khacef, James C. Knight, Laura Kriener, Rajkumar Kubendran, Dhireesha Kudithipudi, Shih-Chii Liu, Yao-Hong Liu, Haoyuan Ma, Rajit Manohar, Josep Maria Margarit-Taulé, Christian Mayr, Konstantinos Michmizos, Dylan R. Muir, Emre Neftci, Thomas Nowotny, Fabrizio Ottati, Ayca Ozcelikkale, Priyadarshini Panda, Jongkil Park, Melika Payvand, Christian Pehle, Mihai A. Petrovici, Christoph Posch, Alpha Renner, Yulia Sandamirskaya, Clemens JS Schaefer, André van Schaik, Johannes Schemmel, Samuel Schmidgall, Catherine Schuman, Jae-sun Seo, Sadique Sheik, Sumit Bam Shrestha, Manolis Sifalakis, Amos Sironi, Kenneth Stewart, Matthew Stewart, Terrence C. Stewart, Jonathan Timcheck, Nergis Tömen, Gianvito Urgese, Marian Verhelst, Craig M. Vineyard, Bernhard Vogginger, Amirreza Yousefzadeh, Fatima Tuz Zohora, Charlotte Frenkel, Vijay Janapa Reddi
To address these shortcomings, we present NeuroBench: a benchmark framework for neuromorphic computing algorithms and systems.
1 code implementation • NIPS 2022 • Li Yang, Jian Meng, Jae-sun Seo, Deliang Fan
In this work, for the first time, we propose a novel alternating sparse training (AST) scheme to train multiple sparse sub-nets for dynamic inference without extra training cost compared to the case of training a single sparse model from scratch.
no code implementations • CVPR 2022 • Jian Meng, Li Yang, Jinwoo Shin, Deliang Fan, Jae-sun Seo
Contrastive learning (or its variants) has recently become a promising direction in the self-supervised learning domain, achieving similar performance as supervised learning with minimum fine-tuning.
no code implementations • 14 Aug 2021 • Gokul Krishnan, Sumit K. Mandal, Manvitha Pannala, Chaitali Chakrabarti, Jae-sun Seo, Umit Y. Ogras, Yu Cao
In-memory computing (IMC) on a monolithic chip for deep learning faces dramatic challenges on area, yield, and on-chip interconnection cost due to the ever-increasing model sizes.
no code implementations • 6 Jul 2021 • Gokul Krishnan, Sumit K. Mandal, Chaitali Chakrabarti, Jae-sun Seo, Umit Y. Ogras, Yu Cao
In this technique, we use analytical models of NoC to evaluate end-to-end communication latency of any given DNN.
no code implementations • 22 Mar 2021 • Adnan Siraj Rakin, Li Yang, Jingtao Li, Fan Yao, Chaitali Chakrabarti, Yu Cao, Jae-sun Seo, Deliang Fan
Apart from recovering the inference accuracy, our RA-BNN after growing also shows significantly higher resistance to BFA.
no code implementations • 10 Feb 2021 • Vinay Joshi, Wangxin He, Jae-sun Seo, Bipin Rajendran
We propose a hybrid in-memory computing (HIC) architecture for the training of DNNs on hardware accelerators that results in memory-efficient inference and outperforms baseline software accuracy in benchmark tasks.
2 code implementations • 10 Mar 2020 • Colby R. Banbury, Vijay Janapa Reddi, Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, Robert Hurtado, David Kanter, Anton Lokhmotov, David Patterson, Danilo Pau, Jae-sun Seo, Jeff Sieracki, Urmish Thakker, Marian Verhelst, Poonam Yadav
In this position paper, we present the current landscape of TinyML and discuss the challenges and direction towards developing a fair and useful hardware benchmark for TinyML workloads.
no code implementations • 25 Sep 2019 • Shihui Yin, Kyu-Hyoun Kim, Jinwook Oh, Naigang Wang, Mauricio Serrano, Jae-sun Seo, Jungwook Choi
In the case of ResNet50 on ImageNet, this comes to the winning ticket of 75:02% Top-1 accuracy at 80% pruning rate in only 22% of the total epochs for iterative pruning.
no code implementations • 16 Sep 2019 • Shihui Yin, Xiaoyu Sun, Shimeng Yu, Jae-sun Seo
In this work, we demonstrate a scalable RRAM based in-memory computing design, termed XNOR-RRAM, which is fabricated in a 90nm CMOS technology with monolithic integration of RRAM devices between metal 1 and 2.
no code implementations • 15 Aug 2019 • Shreyas Kolala Venkataramanaiah, Yufei Ma, Shihui Yin, Eriko Nurvithadhi, Aravind Dasu, Yu Cao, Jae-sun Seo
Training of convolutional neural networks (CNNs)on embedded platforms to support on-device learning is earning vital importance in recent days.
1 code implementation • 27 Feb 2019 • Paul N. Whatmough, Chuteng Zhou, Patrick Hansen, Shreyas Kolala Venkataramanaiah, Jae-sun Seo, Matthew Mattina
Over a suite of six datasets we trained models via transfer learning with an accuracy loss of $<1\%$ resulting in up to 11. 2 TOPS/W - nearly $2 \times$ more efficient than a conventional programmable CNN accelerator of the same area.
no code implementations • 23 May 2018 • Chetan Singh Thakur, Jamal Molin, Gert Cauwenberghs, Giacomo Indiveri, Kundan Kumar, Ning Qiao, Johannes Schemmel, Runchun Wang, Elisabetta Chicca, Jennifer Olson Hasler, Jae-sun Seo, Shimeng Yu, Yu Cao, André van Schaik, Ralph Etienne-Cummings
Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems.
no code implementations • 19 Apr 2018 • Shihui Yin, Gaurav Srivastava, Shreyas K. Venkataramanaiah, Chaitali Chakrabarti, Visar Berisha, Jae-sun Seo
Deep learning algorithms have shown tremendous success in many recognition tasks; however, these algorithms typically include a deep neural network (DNN) structure and a large number of parameters, which makes it challenging to implement them on power/area-constrained embedded platforms.
1 code implementation • 19 Sep 2017 • Shihui Yin, Shreyas K. Venkataramanaiah, Gregory K. Chen, Ram Krishnamurthy, Yu Cao, Chaitali Chakrabarti, Jae-sun Seo
We present a new back propagation based training algorithm for discrete-time spiking neural networks (SNN).
no code implementations • 29 Sep 2016 • R. Tapiador, A. Rios-Navarro, A. Linares-Barranco, Minkyu Kim, Deepak Kadetotad, Jae-sun Seo
Many-core GPU architectures show superior performance but they consume high power and also have memory constraints due to inconsistencies between cache and main memory.
no code implementations • 16 May 2016 • Ming Tu, Visar Berisha, Yu Cao, Jae-sun Seo
In this paper, we propose a method to compress deep neural networks by using the Fisher Information metric, which we estimate through a stochastic optimization method that keeps track of second-order information in the network.