default search action
Diana Marculescu
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [c147]Tanvir Mahmud, Shentong Mo, Yapeng Tian, Diana Marculescu:
MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers. CVPR Workshops 2024: 7996-8005 - [c146]Ning-Chi Huang, Chi-Chih Chang, Wei-Cheng Lin, Endri Taka, Diana Marculescu, Kai-Chiang Wu:
ELSA: Exploiting Layer-wise N: M Sparsity for Vision Transformer Acceleration. CVPR Workshops 2024: 8006-8015 - [c145]Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu:
Cache and Reuse: Rethinking the Efficiency of On-device Transfer Learning. CVPR Workshops 2024: 8040-8049 - [c144]Feng Liang, Bichen Wu, Jialiang Wang, Licheng Yu, Kunpeng Li, Yinan Zhao, Ishan Misra, Jia-Bin Huang, Peizhao Zhang, Peter Vajda, Diana Marculescu:
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis. CVPR 2024: 8207-8216 - [c143]Tanvir Mahmud, Yapeng Tian, Diana Marculescu:
T-VSL: Text-Guided Visual Sound Source Localization in Mixtures. CVPR 2024: 26732-26741 - [c142]Endri Taka, Dimitrios Gourounas, Andreas Gerstlauer, Diana Marculescu, Aman Arora:
Efficient Approaches for GEMM Acceleration on Leading AI-Optimized FPGAs. FCCM 2024: 54-65 - [c141]Tanvir Mahmud, Saeed Amizadeh, Kazuhito Koishida, Diana Marculescu:
Weakly-supervised Audio Separation via Bi-modal Semantic Similarity. ICLR 2024 - [c140]Chi-Chih Chang, Yuan-Yao Sung, Shixing Yu, Ning-Chi Huang, Diana Marculescu, Kai-Chiang Wu:
FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer. WACV 2024: 2470-2479 - [c139]Tanvir Mahmud, Chun-Hao Liu, Burhaneddin Yaman, Diana Marculescu:
SSVOD: Semi-Supervised Video Object Detection with Sparse Annotations. WACV 2024: 6759-6768 - [i57]Tanvir Mahmud, Burhaneddin Yaman, Chun-Hao Liu, Diana Marculescu:
PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference. CoRR abs/2403.16020 (2024) - [i56]Tanvir Mahmud, Saeed Amizadeh, Kazuhito Koishida, Diana Marculescu:
Weakly-supervised Audio Separation via Bi-modal Semantic Similarity. CoRR abs/2404.01740 (2024) - [i55]Tanvir Mahmud, Yapeng Tian, Diana Marculescu:
T-VSL: Text-Guided Visual Sound Source Localization in Mixtures. CoRR abs/2404.01751 (2024) - [i54]Endri Taka, Dimitrios Gourounas, Andreas Gerstlauer, Diana Marculescu, Aman Arora:
Efficient Approaches for GEMM Acceleration on Leading AI-Optimized FPGAs. CoRR abs/2404.11066 (2024) - [i53]Feng Liang, Akio Kodaira, Chenfeng Xu, Masayoshi Tomizuka, Kurt Keutzer, Diana Marculescu:
Looking Backward: Streaming Video-to-Video Translation with Feature Banks. CoRR abs/2405.15757 (2024) - [i52]Tanvir Mahmud, Mustafa Munir, Radu Marculescu, Diana Marculescu:
Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior. CoRR abs/2406.04873 (2024) - [i51]Tanvir Mahmud, Shentong Mo, Yapeng Tian, Diana Marculescu:
MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers. CoRR abs/2406.04930 (2024) - [i50]Hung-Yueh Chiang, Diana Marculescu:
SCAN-Edge: Finding MobileNet-speed Hybrid Networks for Diverse Edge Devices via Hardware-Aware Evolutionary Search. CoRR abs/2408.15395 (2024) - [i49]Ning-Chi Huang, Chi-Chih Chang, Wei-Cheng Lin, Endri Taka, Diana Marculescu, Kai-Chiang Wu:
ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration. CoRR abs/2409.09708 (2024) - [i48]Tanvir Mahmud, Diana Marculescu:
OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation. CoRR abs/2409.19270 (2024) - 2023
- [j58]Ahmet Inci, Siri Garudanagiri Virupaksha, Aman Jain, Ting-Wu Chin, Venkata Vivek Thallam, Ruizhou Ding, Diana Marculescu:
QUIDAM: A Framework for Quantization-aware DNN Accelerator and Model Co-Exploration. ACM Trans. Embed. Comput. Syst. 22(2): 33:1-33:21 (2023) - [c138]Hung-Yueh Chiang, Natalia Frumkin, Feng Liang, Diana Marculescu:
MobileTL: On-Device Transfer Learning with Inverted Residual Blocks. AAAI 2023: 7166-7174 - [c137]Feng Liang, Bichen Wu, Xiaoliang Dai, Kunpeng Li, Yinan Zhao, Hang Zhang, Peizhao Zhang, Peter Vajda, Diana Marculescu:
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP. CVPR 2023: 7061-7070 - [c136]Endri Taka, Aman Arora, Kai-Chiang Wu, Diana Marculescu:
MaxEVA: Maximizing the Efficiency of Matrix Multiplication on Versal AI Engine. ICFPT 2023: 96-105 - [c135]Tanvir Mahmud, Feng Liang, Yaling Qing, Diana Marculescu:
CLIP4VideoCap: Rethinking Clip for Video Captioning with Multiscale Temporal Fusion and Commonsense Knowledge. ICASSP 2023: 1-5 - [c134]Natalia Frumkin, Dibakar Gope, Diana Marculescu:
Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers. ICCV 2023: 16932-16942 - [c133]Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu:
Efficient Low-rank Backpropagation for Vision Transformer Adaptation. NeurIPS 2023 - [c132]Tanvir Mahmud, Diana Marculescu:
AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization. WACV 2023: 5147-5156 - [i47]Natalia Frumkin, Dibakar Gope, Diana Marculescu:
Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers. CoRR abs/2308.10814 (2023) - [i46]Tanvir Mahmud, Chun-Hao Liu, Burhaneddin Yaman, Diana Marculescu:
SSVOD: Semi-Supervised Video Object Detection with Sparse Annotations. CoRR abs/2309.01391 (2023) - [i45]Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu:
Efficient Low-rank Backpropagation for Vision Transformer Adaptation. CoRR abs/2309.15275 (2023) - [i44]Chi-Chih Chang, Yuan-Yao Sung, Shixing Yu, Ning-Chi Huang, Diana Marculescu, Kai-Chiang Wu:
FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer. CoRR abs/2311.03912 (2023) - [i43]Endri Taka, Aman Arora, Kai-Chiang Wu, Diana Marculescu:
MaxEVA: Maximizing the Efficiency of Matrix Multiplication on Versal AI Engine. CoRR abs/2311.04980 (2023) - [i42]Feng Liang, Bichen Wu, Jialiang Wang, Licheng Yu, Kunpeng Li, Yinan Zhao, Ishan Misra, Jia-Bin Huang, Peizhao Zhang, Peter Vajda, Diana Marculescu:
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis. CoRR abs/2312.17681 (2023) - 2022
- [j57]Ahmet Inci, Mehmet Meric Isgenc, Diana Marculescu:
DeepNVM++: Cross-Layer Modeling and Optimization Framework of Nonvolatile Memories for Deep Learning. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 41(10): 3426-3437 (2022) - [c131]Feng Liang, Ting-Wu Chin, Yang Zhou, Diana Marculescu:
ANT: Adapt Network Across Time for Efficient Video Processing. CVPR Workshops 2022: 2602-2607 - [e5]Diana Marculescu, Yuejie Chi, Carole-Jean Wu:
Proceedings of the Fifth Conference on Machine Learning and Systems, MLSys 2022, Santa Clara, CA, USA, August 29 - September 1, 2022. mlsys.org 2022 [contents] - [i41]Ahmet Inci, Siri Garudanagiri Virupaksha, Aman Jain, Venkata Vivek Thallam, Ruizhou Ding, Diana Marculescu:
QAPPA: Quantization-Aware Power, Performance, and Area Modeling of DNN Accelerators. CoRR abs/2205.08648 (2022) - [i40]Ahmet Inci, Siri Garudanagiri Virupaksha, Aman Jain, Venkata Vivek Thallam, Ruizhou Ding, Diana Marculescu:
QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimality. CoRR abs/2205.13045 (2022) - [i39]Feng Liang, Yangguang Li, Diana Marculescu:
SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners. CoRR abs/2205.14540 (2022) - [i38]Yang Zhou, Feng Liang, Ting-Wu Chin, Diana Marculescu:
Play It Cool: Dynamic Shifting Prevents Thermal Throttling. CoRR abs/2206.10849 (2022) - [i37]Ahmet Inci, Mehmet Meric Isgenc, Diana Marculescu:
Efficient Deep Learning Using Non-Volatile Memory Technology. CoRR abs/2206.13601 (2022) - [i36]Ahmet Inci, Siri Garudanagiri Virupaksha, Aman Jain, Ting-Wu Chin, Venkata Vivek Thallam, Ruizhou Ding, Diana Marculescu:
QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration. CoRR abs/2206.15463 (2022) - [i35]Feng Liang, Bichen Wu, Xiaoliang Dai, Kunpeng Li, Yinan Zhao, Hang Zhang, Peizhao Zhang, Peter Vajda, Diana Marculescu:
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP. CoRR abs/2210.04150 (2022) - [i34]Tanvir Mahmud, Diana Marculescu:
AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization. CoRR abs/2210.05060 (2022) - [i33]Natalia Frumkin, Dibakar Gope, Diana Marculescu:
CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers. CoRR abs/2211.09643 (2022) - [i32]Hung-Yueh Chiang, Natalia Frumkin, Feng Liang, Diana Marculescu:
MobileTL: On-device Transfer Learning with Inverted Residual Blocks. CoRR abs/2212.03246 (2022) - 2021
- [c130]Ting-Wu Chin, Diana Marculescu, Ari S. Morcos:
Width Transfer: On the (In)variance of Width Optimization. CVPR Workshops 2021: 2990-2999 - [c129]Ting-Wu Chin, Cha Zhang, Diana Marculescu:
Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness. CVPR Workshops 2021: 3243-3252 - [c128]Diana Marculescu:
When Climate Meets Machine Learning: Edge to Cloud ML Energy Efficiency. ISLPED 2021: 1 - [c127]Ting-Wu Chin, Ari S. Morcos, Diana Marculescu:
Joslim: Joint Widths and Weights Optimization for Slimmable Neural Networks. ECML/PKDD (3) 2021: 119-134 - [c126]Ting-Wu Chin, Dimitrios Stamoulis, Diana Marculescu:
Putting the "Machine" Back in Machine Learning for Engineering Students. Teaching ML 2021: 78-82 - [i31]Ting-Wu Chin, Diana Marculescu, Ari S. Morcos:
Width Transfer: On the (In)variance of Width Optimization. CoRR abs/2104.13255 (2021) - 2020
- [j56]Lixin Fan, Diana Marculescu, Werner Bailer, Yurong Chen:
Editorial: Special Issue on Compact Deep Neural Networks With Industrial Applications. IEEE J. Sel. Top. Signal Process. 14(4): 605-608 (2020) - [j55]Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu:
Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization. IEEE J. Sel. Top. Signal Process. 14(4): 609-622 (2020) - [c125]Ting-Wu Chin, Ruizhou Ding, Cha Zhang, Diana Marculescu:
Towards Efficient Model Compression via Learned Global Ranking. CVPR 2020: 1515-1525 - [c124]Ahmet Fatih Inci, Mehmet Meric Isgenc, Diana Marculescu:
DeepNVM: A Framework for Modeling and Analysis of Non-Volatile Memory Technologies for Deep Learning Applications. DATE 2020: 1295-1298 - [c123]Ting-Wu Chin, Pierce I-Jen Chuang, Vikas Chandra, Diana Marculescu:
One Weight Bitwidth to Rule Them All. ECCV Workshops (5) 2020: 85-103 - [c122]Radu Marculescu, Diana Marculescu, Ümit Y. Ogras:
Edge AI: Systems Design and ML for IoT Data Analytics. KDD 2020: 3565-3566 - [c121]Zhuo Chen, Jiyuan Zhang, Ruizhou Ding, Diana Marculescu:
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection. WACV 2020: 1169-1178 - [i30]Ting-Wu Chin, Cha Zhang, Diana Marculescu:
Improving the Adversarial Robustness of Transfer Learning via Noisy Feature Distillation. CoRR abs/2002.02998 (2020) - [i29]R. Iris Bahar, Alex K. Jones, Srinivas Katkoori, Patrick H. Madden, Diana Marculescu, Igor L. Markov:
Workshops on Extreme Scale Design Automation (ESDA) Challenges and Opportunities for 2025 and Beyond. CoRR abs/2005.01588 (2020) - [i28]Ting-Wu Chin, Ari S. Morcos, Diana Marculescu:
PareCO: Pareto-aware Channel Optimization for Slimmable Neural Networks. CoRR abs/2007.11752 (2020) - [i27]Ting-Wu Chin, Pierce I-Jen Chuang, Vikas Chandra, Diana Marculescu:
One Weight Bitwidth to Rule Them All. CoRR abs/2008.09916 (2020) - [i26]Ahmet Fatih Inci, Evgeny Bolotin, Yaosheng Fu, Gal Dalal, Shie Mannor, David W. Nellans, Diana Marculescu:
The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems. CoRR abs/2012.04210 (2020) - [i25]Ahmet Inci, Mehmet Meric Isgenc, Diana Marculescu:
DeepNVM++: Cross-Layer Modeling and Optimization Framework of Non-Volatile Memories for Deep Learning. CoRR abs/2012.04559 (2020)
2010 – 2019
- 2019
- [j54]Biresh Kumar Joardar, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
Learning-Based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems. IEEE Trans. Computers 68(6): 852-866 (2019) - [j53]Ifigeneia Apostolopoulou, Diana Marculescu:
Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks. IEEE Trans. Neural Networks Learn. Syst. 30(9): 2720-2734 (2019) - [c120]Ruizhou Ding, Ting-Wu Chin, Zeye Liu, Diana Marculescu:
Regularizing Activation Distribution for Training Binarized Deep Networks. CVPR 2019: 11408-11417 - [c119]Ruizhou Ding, Zeye Liu, Ting-Wu Chin, Diana Marculescu, R. D. (Shawn) Blanton:
FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference. DAC 2019: 200 - [c118]Ting-Wu Chin, Ruizhou Ding, Diana Marculescu:
AdaScale: Towards Real-time Video Object Detection using Adaptive Scaling. SysML 2019 - [c117]Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu:
Single-Path NAS: Designing Hardware-Efficient ConvNets in Less Than 4 Hours. ECML/PKDD (2) 2019: 481-497 - [i24]Zhuo Chen, Ruizhou Ding, Ting-Wu Chin, Diana Marculescu:
Understanding the Impact of Label Granularity on CNN-based Image Classification. CoRR abs/1901.07012 (2019) - [i23]Ting-Wu Chin, Ruizhou Ding, Diana Marculescu:
AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling. CoRR abs/1902.02910 (2019) - [i22]Ruizhou Ding, Ting-Wu Chin, Zeye Liu, Diana Marculescu:
Regularizing Activation Distribution for Training Binarized Deep Networks. CoRR abs/1904.02823 (2019) - [i21]Ruizhou Ding, Zeye Liu, Ting-Wu Chin, Diana Marculescu, Ronald D. Blanton:
FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference. CoRR abs/1904.02835 (2019) - [i20]Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu:
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours. CoRR abs/1904.02877 (2019) - [i19]Ting-Wu Chin, Ruizhou Ding, Cha Zhang, Diana Marculescu:
LeGR: Filter Pruning via Learned Global Ranking. CoRR abs/1904.12368 (2019) - [i18]Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu:
Single-Path NAS: Device-Aware Efficient ConvNet Design. CoRR abs/1905.04159 (2019) - [i17]Zhuo Chen, Jiyuan Zhang, Ruizhou Ding, Diana Marculescu:
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection. CoRR abs/1906.07912 (2019) - [i16]Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu:
Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization. CoRR abs/1907.00959 (2019) - 2018
- [j52]Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis. Computer 51(7): 66-77 (2018) - [j51]Wonje Choi, Karthi Duraisamy, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
On-Chip Communication Network for Efficient Training of Deep Convolutional Networks on Heterogeneous Manycore Systems. IEEE Trans. Computers 67(5): 672-686 (2018) - [j50]Zhuo Chen, Dimitrios Stamoulis, Diana Marculescu:
Profit: Priority and Power/Performance Optimization for Many-Core Systems. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 37(10): 2064-2075 (2018) - [j49]Ruizhou Ding, Zeye Liu, R. D. (Shawn) Blanton, Diana Marculescu:
Lightening the Load with Highly Accurate Storage- and Energy-Efficient LightNNs. ACM Trans. Reconfigurable Technol. Syst. 11(3): 17:1-17:24 (2018) - [c116]Ruizhou Ding, Zeye Liu, R. D. (Shawn) Blanton, Diana Marculescu:
Quantized deep neural networks for energy efficient hardware-based inference. ASP-DAC 2018: 1-8 - [c115]Dimitrios Stamoulis, Ermao Cai, Da-Cheng Juan, Diana Marculescu:
HyperPower: Power- and memory-constrained hyper-parameter optimization for neural networks. DATE 2018: 19-24 - [c114]Dimitrios Stamoulis, Ting-Wu (Rudy) Chin, Anand Krishnan Prakash, Haocheng Fang, Sribhuvan Sajja, Mitchell Bognar, Diana Marculescu:
Designing adaptive neural networks for energy-constrained image classification. ICCAD 2018: 23 - [c113]Biresh Kumar Joardar, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
Hybrid on-chip communication architectures for heterogeneous manycore systems. ICCAD 2018: 62 - [c112]Diana Marculescu, Dimitrios Stamoulis, Ermao Cai:
Hardware-aware machine learning: modeling and optimization. ICCAD 2018: 137 - [c111]Zhuo Chen, Ruizhou Ding, Ting-Wu Chin, Diana Marculescu:
Understanding the Impact of Label Granularity on CNN-Based Image Classification. ICDM Workshops 2018: 895-904 - [i15]Ifigeneia Apostolopoulou, Diana Marculescu:
Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks. CoRR abs/1801.07693 (2018) - [i14]Ruizhou Ding, Zeye Liu, Rongye Shi, Diana Marculescu, R. D. (Shawn) Blanton:
LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks. CoRR abs/1802.02178 (2018) - [i13]Dimitrios Stamoulis, Ting-Wu (Rudy) Chin, Anand Krishnan Prakash, Haocheng Fang, Sribhuvan Sajja, Mitchell Bognar, Diana Marculescu:
Designing Adaptive Neural Networks for Energy-Constrained Image Classification. CoRR abs/1808.01550 (2018) - [i12]Diana Marculescu, Dimitrios Stamoulis, Ermao Cai:
Hardware-Aware Machine Learning: Modeling and Optimization. CoRR abs/1809.05476 (2018) - [i11]Ting-Wu Chin, Cha Zhang, Diana Marculescu:
Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks. CoRR abs/1810.00518 (2018) - [i10]Biresh Kumar Joardar, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems. CoRR abs/1810.08869 (2018) - 2017
- [j48]Yatish Turakhia, Guangshuo Liu, Siddharth Garg, Diana Marculescu:
Thread Progress Equalization: Dynamically Adaptive Power-Constrained Performance Optimization of Multi-Threaded Applications. IEEE Trans. Computers 66(4): 731-744 (2017) - [j47]Ermao Cai, Diana Marculescu:
Temperature Effect Inversion-Aware Power-Performance Optimization for FinFET-Based Multicore Systems. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 36(11): 1897-1910 (2017) - [j46]Ryan Gary Kim, Wonje Choi, Zhuo Chen, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
Imitation Learning for Dynamic VFI Control in Large-Scale Manycore Systems. IEEE Trans. Very Large Scale Integr. Syst. 25(9): 2458-2471 (2017) - [c110]Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, Diana Marculescu:
\emphNeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks. ACML 2017: 622-637 - [c109]Ruizhou Ding, Dimitrios Stamoulis, Kartikeya Bhardwaj, Diana Marculescu, Radu Marculescu:
Enhancing precipitation models by capturing multivariate and multiscale climate dynamics. CySWATER@CPSWeek 2017: 39-42 - [c108]Da-Cheng Juan, Neil Shah, Mingyu Tang, Zhiliang Qian, Diana Marculescu, Christos Faloutsos:
M3A: Model, MetaModel and Anomaly Detection for Inter-arrivals of Web Searches and Postings. DSAA 2017: 341-350 - [c107]Ruizhou Ding, Diana Marculescu:
Leveraging Classification Models for River Forecasting. SIGSPATIAL/GIS 2017: 83:1-83:4 - [c106]Ruizhou Ding, Zeye Liu, Rongye Shi, Diana Marculescu, R. D. (Shawn) Blanton:
LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks. ACM Great Lakes Symposium on VLSI 2017: 35-40 - [c105]Biresh Kumar Joardar, Wonje Choi, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
3D NoC-Enabled Heterogeneous Manycore Architectures for Accelerating CNN Training: Performance and Thermal Trade-offs. NOCS 2017: 18:1-18:8 - [i9]Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, Diana Marculescu:
NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks. CoRR abs/1710.05420 (2017) - [i8]Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis. CoRR abs/1712.00076 (2017) - [i7]Wonje Choi, Karthi Duraisamy, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
On-Chip Communication Network for Efficient Training of Deep Convolutional Networks on Heterogeneous Manycore Systems. CoRR abs/1712.02293 (2017) - [i6]Dimitrios Stamoulis, Ermao Cai, Da-Cheng Juan, Diana Marculescu:
HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks. CoRR abs/1712.02446 (2017) - [i5]Zhuo Chen, Diana Marculescu:
Task Scheduling for Heterogeneous Multicore Systems. CoRR abs/1712.03209 (2017) - [i4]Zhuo Chen, Diana Marculescu:
Priority-Aware Near-Optimal Scheduling for Heterogeneous Multi-Core Systems with Specialized Accelerators. CoRR abs/1712.03246 (2017) - 2016
- [j45]Jiajia Jiao, Diana Marculescu, Da-Cheng Juan, Yuzhuo Fu:
A two-level approximate model driven framework for characterizing Multi-Cell Upsets impacts on processors. Microelectron. J. 48: 7-17 (2016) - [j44]Ryan Gary Kim, Wonje Choi, Guangshuo Liu, Ehsan Mohandesi, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
Wireless NoC for VFI-Enabled Multicore Chip Design: Performance Evaluation and Design Trade-Offs. IEEE Trans. Computers 65(4): 1323-1336 (2016) - [j43]Zhiliang Qian, Da-Cheng Juan, Paul Bogdan, Chi-Ying Tsui, Diana Marculescu, Radu Marculescu:
A Support Vector Regression (SVR)-Based Latency Model for Network-on-Chip (NoC) Architectures. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 35(3): 471-484 (2016) - [j42]Ermao Cai, Da-Cheng Juan, Siddharth Garg, Jinpyo Park, Diana Marculescu:
Learning-Based Power/Performance Optimization for Many-Core Systems With Extended-Range Voltage/Frequency Scaling. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 35(8): 1318-1331 (2016) - [j41]Ryan Gary Kim, Wonje Choi, Zhuo Chen, Partha Pratim Pande, Diana Marculescu, Radu Marculescu:
Wireless NoC and Dynamic VFI Codesign: Energy Efficiency Without Performance Penalty. IEEE Trans. Very Large Scale Integr. Syst. 24(7): 2488-2501 (2016) - [c104]Wonje Choi, Karthi Duraisamy, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Radu Marculescu, Diana Marculescu:
Hybrid network-on-chip architectures for accelerating deep learning kernels on heterogeneous manycore platforms. CASES 2016: 13:1-13:10 - [c103]