Zobrazeno 1 - 10
of 7 943
pro vyhledávání: '"P., Manjunath"'
We analyze the effect that online algorithms have on the environment that they are learning. As a motivation, consider recommendation systems that use online algorithms to learn optimal product recommendations based on user and product attributes. It
Externí odkaz:
http://arxiv.org/abs/2411.13883
This paper investigates the feasibility of class-incremental learning (CIL) for Sound Event Localization and Detection (SELD) tasks. The method features an incremental learner that can learn new sound classes independently while preserving knowledge
Externí odkaz:
http://arxiv.org/abs/2411.12830
Autor:
Krishnapur, Manjunath, Yogeshwaran, D.
We consider covariance asymptotics for linear statistics of general stationary random measures in terms of their truncated pair correlation measure. We give exact infinite series-expansion formulas for covariance of smooth statistics of random measur
Externí odkaz:
http://arxiv.org/abs/2411.08848
Sleep staging is a challenging task, typically manually performed by sleep technologists based on electroencephalogram and other biosignals of patients taken during overnight sleep studies. Recent work aims to leverage automated algorithms to perform
Externí odkaz:
http://arxiv.org/abs/2411.07964
Autor:
Manjunath, Yoga Suhas Kuruba, Szymanowski, Mathew, Wissborn, Austin, Li, Mushu, Zhao, Lian, Zhang, Xiao-Ping
Our work proposes a comprehensive solution for predicting Metaverse network traffic, addressing the growing demand for intelligent resource management in eXtended Reality (XR) services. We first introduce a state-of-the-art testbed capturing a real-w
Externí odkaz:
http://arxiv.org/abs/2411.11894
Autor:
Manjunath, Yoga Suhas Kuruba, Wissborn, Austin, Szymanowski, Mathew, Li, Mushu, Zhao, Lian, Zhang, Xiao-Ping
In this paper, we design an exclusive Metaverse network traffic classifier, named Discern-XR, to help Internet service providers (ISP) and router manufacturers enhance the quality of Metaverse services. Leveraging segmented learning, the Frame Vector
Externí odkaz:
http://arxiv.org/abs/2411.05184
Autor:
Kumar, Shashi, Thorbecke, Iuliia, Burdisso, Sergio, Villatoro-Tello, Esaú, E, Manjunath K, Hacioğlu, Kadri, Rangappa, Pradeep, Motlicek, Petr, Ganapathiraju, Aravind, Stolcke, Andreas
Recent research has demonstrated that training a linear connector between speech foundation encoders and large language models (LLMs) enables this architecture to achieve strong ASR capabilities. Despite the impressive results, it remains unclear whe
Externí odkaz:
http://arxiv.org/abs/2411.03866
Autor:
D, Manjunath, Gurunath, Prajwal, Udupa, Sumanth, Gandhamal, Aditya, Madhu, Shrikar, Sikdar, Aniruddh, Sundaram, Suresh
Deep neural networks (DNNs) have shown exceptional performance when trained on well-illuminated images captured by Electro-Optical (EO) cameras, which provide rich texture details. However, in critical applications like aerial perception, it is essen
Externí odkaz:
http://arxiv.org/abs/2410.20953
This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) inste
Externí odkaz:
http://arxiv.org/abs/2410.15608
Autor:
Manjunath, Madhusudan
We study the theory of equations in one variable over polyhedral semirings. The article revolves around a notion of solution to a polynomial equation over a polyhedral semiring. Our main results are a characterisation of local solutions in terms of t
Externí odkaz:
http://arxiv.org/abs/2410.15426