Zobrazeno 1 - 10
of 16 024
pro vyhledávání: '"Darshan, A."'
Active Learning (AL) is a user-interactive approach aimed at reducing annotation costs by selecting the most crucial examples to label. Although AL has been extensively studied for image classification tasks, the specific scenario of interactive imag
Externí odkaz:
http://arxiv.org/abs/2412.02310
Image restoration aims to recover high-quality images from degraded observations. When the degradation process is known, the recovery problem can be formulated as an inverse problem, and in a Bayesian context, the goal is to sample a clean reconstruc
Externí odkaz:
http://arxiv.org/abs/2411.15295
Autor:
Delaunay, Pierre, Bouthillier, Xavier, Breuleux, Olivier, Ortiz-Gagné, Satya, Bilaniuk, Olexa, Normandin, Fabrice, Bergeron, Arnaud, Carrez, Bruno, Alain, Guillaume, Blanc, Soline, Osterrath, Frédéric, Viviano, Joseph, Patil, Roger Creus-Castanyer Darshan, Awal, Rabiul, Zhang, Le
AI workloads, particularly those driven by deep learning, are introducing novel usage patterns to high-performance computing (HPC) systems that are not comprehensively captured by standard HPC benchmarks. As one of the largest academic research cente
Externí odkaz:
http://arxiv.org/abs/2411.11940
Autor:
Balasubramanian, S, Subramaniam, M Sai, Talasu, Sai Sriram, Krishna, P Yedu, Sai, Manepalli Pranav Phanindra, Mukkamala, Ravi, Gera, Darshan
Deep neural networks (DNNS) excel at learning from static datasets but struggle with continual learning, where data arrives sequentially. Catastrophic forgetting, the phenomenon of forgetting previously learned knowledge, is a primary challenge. This
Externí odkaz:
http://arxiv.org/abs/2410.23751
Autor:
Koeplinger, David, Gandhi, Darshan, Nandkar, Pushkar, Sheeley, Nathan, Musaddiq, Matheen, Zhang, Leon, Goodbar, Reid, Shaffer, Matthew, Wang, Han, Wang, Angela, Wang, Mingran, Prabhakar, Raghu
Token generation speed is critical to power the next wave of AI inference applications. GPUs significantly underperform during token generation due to synchronization overheads at kernel boundaries, utilizing only 21% of their peak memory bandwidth.
Externí odkaz:
http://arxiv.org/abs/2410.23668
Autor:
Middleton, Alicia, Choi, Steve K., Walker, Samantha, Austermann, Jason, Burgoyne, James R., Butler, Victoria, Chapman, Scott C., Crites, Abigail T., Duell, Cody J., Freundt, Rodrigo G., Huber, Anthony I., Huber, Zachary B., Hubmayr, Johannes, Keller, Ben, Lin, Lawrence T., Niemack, Michael D., Patel, Darshan, Sinclair, Adrian K., Smith, Ema, Vaskuri, Anna, Vavagiakis, Eve M., Vissers, Michael, Wang, Yuhan, Wheeler, Jordan
Prime-Cam, one of the primary instruments for the Fred Young Submillimeter Telescope (FYST) developed by the CCAT Collaboration, will house up to seven instrument modules, with the first operating at 280 GHz. Each module will include three arrays of
Externí odkaz:
http://arxiv.org/abs/2410.21396
Activation functions introduce non-linearity into Neural Networks, enabling them to learn complex patterns. Different activation functions vary in speed and accuracy, ranging from faster but less accurate options like ReLU to slower but more accurate
Externí odkaz:
http://arxiv.org/abs/2410.10887
Autor:
Bangad, Nikhil, Jayaram, Vivekananda, Krishnappa, Manjunatha Sughaturu, Banarse, Amey Ram, Bidkar, Darshan Mohan, Nagpal, Akshay, Parlapalli, Vidyasagar
Publikováno v:
International Journal of Computer Engineering and Technology IJCET 2024
This paper presents a theoretical framework for an AI-driven data quality monitoring system designed to address the challenges of maintaining data quality in high-volume environments. We examine the limitations of traditional methods in managing the
Externí odkaz:
http://arxiv.org/abs/2410.08576
Dark-field X-ray microscopy (DFXM) is a novel X-ray imaging technique developed at synchrotrons to image along the diffracted beam with a real space resolution of ~100 nm and reciprocal space resolution of $10^{-4}$. Recent implementations of DFXM at
Externí odkaz:
http://arxiv.org/abs/2410.07509
Autor:
Bouchoucha, Rached, Yahmed, Ahmed Haj, Patil, Darshan, Rajendran, Janarthanan, Nikanjam, Amin, Chandar, Sarath, Khomh, Foutse
Deep reinforcement learning (DRL) has shown success in diverse domains such as robotics, computer games, and recommendation systems. However, like any other software system, DRL-based software systems are susceptible to faults that pose unique challe
Externí odkaz:
http://arxiv.org/abs/2410.04322