Zobrazeno 1 - 10
of 6 811
pro vyhledávání: '"Tajana, A."'
Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not show simul
Externí odkaz:
http://arxiv.org/abs/2412.11242
Autor:
Fan, Keming, Moradifirouzabadi, Ashkan, Wu, Xiangjin, Li, Zheyu, Ponzina, Flavio, Persson, Anton, Pop, Eric, Rosing, Tajana, Kang, Mingu
Mass spectrometry (MS) is essential for proteomics and metabolomics but faces impending challenges in efficiently processing the vast volumes of data. This paper introduces SpecPCM, an in-memory computing (IMC) accelerator designed to achieve substan
Externí odkaz:
http://arxiv.org/abs/2411.09760
Autor:
Wang, Zixuan, Mahar, Suyash, Li, Luyi, Park, Jangseon, Kim, Jinpyo, Michailidis, Theodore, Pan, Yue, Rosing, Tajana, Tullsen, Dean, Swanson, Steven, Ryoo, Kyung Chang, Park, Sungjoo, Zhao, Jishen
We present a thorough analysis of the use of CXL-based heterogeneous systems. We built a cluster of server systems that combines different vendor's CPUs and various types of CXL devices. We further developed a heterogeneous memory benchmark suite, He
Externí odkaz:
http://arxiv.org/abs/2411.02814
Autor:
Arbore, Russel, Routh, Xavier, Noor, Abdul Rafae, Kothari, Akash, Yang, Haichao, Xu, Weihong, Pinge, Sumukh, Adve, Vikram, Rosing, Tajana, Zhou, Minxuan
Hyperdimensional Computing (HDC), a technique inspired by cognitive models of computation, has been proposed as an efficient and robust alternative basis for machine learning. HDC programs are often manually written in low-level and target specific l
Externí odkaz:
http://arxiv.org/abs/2410.15179
Mass spectrometry (MS) is essential for protein analysis but faces significant challenges with large datasets and complex post-translational modifications, resulting in difficulties in spectral identification. Open Modification Search (OMS) improves
Externí odkaz:
http://arxiv.org/abs/2409.13361
Autor:
Yang, Haichao, Song, Chang Eun, Xu, Weihong, Khaleghi, Behnam, Mallappa, Uday, Shah, Monil, Fan, Keming, Kang, Mingu, Rosing, Tajana
This paper introduces FSL-HDnn, an energy-efficient accelerator that implements the end-to-end pipeline of feature extraction, classification, and on-chip few-shot learning (FSL) through gradient-free learning techniques in a 40 nm CMOS process. At i
Externí odkaz:
http://arxiv.org/abs/2409.10918
Ensemble learning is a meta-learning approach that combines the predictions of multiple learners, demonstrating improved accuracy and robustness. Nevertheless, ensembling models like Convolutional Neural Networks (CNNs) result in high memory and comp
Externí odkaz:
http://arxiv.org/abs/2409.08369
Processing in-memory (PIM) is promising to accelerate neural networks (NNs) because it minimizes data movement and provides large computational parallelism. Similar to machine learning accelerators, application mapping, which determines the operation
Externí odkaz:
http://arxiv.org/abs/2407.00604
Open Modification Search (OMS) is a promising algorithm for mass spectrometry analysis that enables the discovery of modified peptides. However, OMS encounters challenges as it exponentially extends the search scope. Existing OMS accelerators either
Externí odkaz:
http://arxiv.org/abs/2405.02756
MicroHD: An Accuracy-Driven Optimization of Hyperdimensional Computing Algorithms for TinyML systems
Autor:
Ponzina, Flavio, Rosing, Tajana
Hyperdimensional computing (HDC) is emerging as a promising AI approach that can effectively target TinyML applications thanks to its lightweight computing and memory requirements. Previous works on HDC showed that limiting the standard 10k dimension
Externí odkaz:
http://arxiv.org/abs/2404.00039