Thermally Constrained Codesign of Heterogeneous 3-D Integration of Compute-in-Memory, Digital ML Accelerator, and RISC-V Cores for Mixed ML and Non-ML Workloads von Luo, Yuan-Chun, Lu, Anni, Sharda, Janak, Scherer, Moritz, Tomas Gomez, Jorge, Shakib Sarwar, Syed, Li, Ziyun, Frederick Pinkham, Reid, De Salvo, Barbara, Yu, Shimeng

Volltext

Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing von Sarwar, Syed Shakib, Ankit, Aayush, Roy, Kaushik

Volltext

Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures von Lee, Chankyu, Sarwar, Syed Shakib, Panda, Priyadarshini, Srinivasan, Gopalakrishnan, Roy, Kaushik

Volltext

Siracusa: A 16 nm Heterogenous RISC-V SoC for Extended Reality With At-MRAM Neural Engine von Prasad, Arpan Suravi, Scherer, Moritz, Conti, Francesco, Rossi, Davide, Di Mauro, Alfio, Eggimann, Manuel, Gomez, Jorge Tomas, Li, Ziyun, Sarwar, Syed Shakib, Wang, Zhao, De Salvo, Barbara, Benini, Luca

Volltext

Exploring Memory-Oriented Design Optimization of Edge AI Hardware for Extended Reality Applications von Parmar, Vivek, Sarwar, Syed Shakib, Li, Ziyun, Lee, Hsien-Hsin Sean, Salvo, Barbara De, Suri, Manan

Volltext

Energy Efficient Neural Computing: A Study of Cross-Layer Approximations von Sarwar, Syed Shakib, Srinivasan, Gopalakrishnan, Han, Bing, Wijesinghe, Parami, Jaiswal, Akhilesh, Panda, Priyadarshini, Raghunathan, Anand, Roy, Kaushik

Volltext

Memristor-Based Nonvolatile Random Access Memory: Hybrid Architecture for Low Power Compact Memory Design von Sarwar, Syed Shakib, Saqueb, Syed An Nazmus, Quaiyum, Farhan, Rashid, A. B. M. Harun-Ur

Volltext

Spin-Torque Sensors for Energy Efficient High-Speed Long Interconnects von Al Azim, Zubair, Sengupta, Abhronil, Sarwar, Syed Shakib, Roy, Kaushik

Volltext

Energy-Efficient Neural Computing with Approximate Multipliers von Sarwar, Syed Shakib, Venkataramani, Swagath, Ankit, Aayush, Raghunathan, Anand, Roy, Kaushik

Volltext

Designing Energy-Efficient Intermittently Powered Systems Using Spin-Hall-Effect-Based Nonvolatile SRAM von Raha, Arnab, Jaiswal, Akhilesh, Sarwar, Syed Shakib, Jayakumar, Hrishikesh, Raghunathan, Vijay, Roy, Kaushik

Volltext

Estimating Power, Performance, and Area for On-Sensor Deployment of AR/VR Workloads Using an Analytical Framework von Sun, Xiaoyu, Peng, Xiaochen, Zhang, Sai, Gomez, Jorge, Khwa, Win-San, Sarwar, Syed, Li, Ziyun, Cao, Weidong, Wang, Zhao, Liu, Chiao, Chang, Meng-Fan, Salvo, Barbara, Akarvardar, Kerem, Wong, H.-S. Philip

Volltext

Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures von Lee, Chankyu, Syed Shakib Sarwar, Panda, Priyadarshini, Gopalakrishnan Srinivasan, Kaushik, Roy

Volltext

Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing von Syed Shakib Sarwar, Aayush Ankit, Kaushik, Roy

Volltext

Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks von Syed Shakib Sarwar, Panda, Priyadarshini, Kaushik, Roy

Volltext

Spin-Torque Sensors for Energy Efficient High Speed Long Interconnects von Zubair Al Azim, Sengupta, Abhronil, Syed Shakib Sarwar, Kaushik, Roy

Volltext

x-RAGE: eXtended Reality -- Action & Gesture Events Dataset von Parmar, Vivek, Bane, Dwijay, Sarwar, Syed Shakib, Stangherlin, Kleber, De Salvo, Barbara, Suri, Manan

Volltext bestellen

PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context von Augustin, Maximilian, Sarwar, Syed Shakib, Elhoushi, Mostafa, Zhang, Sai Qian, Li, Yuecheng, De Salvo, Barbara

Volltext bestellen

DRESS: Dynamic REal-time Sparse Subnets von Qu, Zhongnan, Sarwar, Syed Shakib, Dong, Xin, Li, Yuecheng, Sumbul, Ekin, De Salvo, Barbara

Volltext bestellen

Memory-Oriented Design-Space Exploration of Edge-AI Hardware for XR Applications von Parmar, Vivek, Sarwar, Syed Shakib, Li, Ziyun, Lee, Hsien-Hsin S, De Salvo, Barbara, Suri, Manan

Volltext bestellen

SYSTEMS AND METHODS FOR PERFORMING EYE-TRACKING von DE SALVO, Barbara, LIU, Xinqiao, SARWAR, Syed Shakib

Volltext bestellen