Zobrazeno 1 - 10
of 209
pro vyhledávání: '"Baeckström, P."'
Many development decisions affect the results obtained from ML experiments: training data, features, model architecture, hyperparameters, test data, etc. Among these aspects, arguably the most important design decisions are those that involve the eva
Externí odkaz:
http://arxiv.org/abs/2412.03700
Autor:
Vali, Mohammad Hassan, Bäckström, Tom
Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Such latent spaces are difficult to interpret. Some earlier supervised methods aim to create an interpretable latent space or discover inter
Externí odkaz:
http://arxiv.org/abs/2410.20573
Conversational AI (CAI) systems which encompass voice- and text-based assistants are on the rise and have been largely integrated into people's everyday lives. Despite their widespread adoption, users voice concerns regarding privacy, security and tr
Externí odkaz:
http://arxiv.org/abs/2406.09037
Autor:
Balouji, Ebrahim, Bäckström, Karl, Olsson, Viktor, Hovila, Petri, Niveri, Henry, Kulmala, Anna, Salo, Ari
As society becomes increasingly reliant on electricity, the reliability requirements for electricity supply continue to rise. In response, transmission/distribution system operators (T/DSOs) must improve their networks and operational practices to re
Externí odkaz:
http://arxiv.org/abs/2306.12724
Autor:
Bäckström, Tom
Speech technology for communication, accessing information and services has rapidly improved in quality. It is convenient and appealing because speech is the primary mode of communication for humans. Such technology however also presents proven threa
Externí odkaz:
http://arxiv.org/abs/2305.05227
Autor:
Perrey, Hanno, Ros, Linus, Elfman, Mikael, Bäckström, Ulrika, Kristiansson, Per, Sjöland, Anders
The reliable detection of neutrons in a harsh gamma-ray environment is an important aspect of establishing non-destructive methods for the characterization of spent nuclear fuel. In this study, we present results from extended in-situ monitoring of d
Externí odkaz:
http://arxiv.org/abs/2107.01047
Stochastic gradient descent (SGD) is an essential element in Machine Learning (ML) algorithms. Asynchronous parallel shared-memory SGD (AsyncSGD), including synchronization-free algorithms, e.g. HOGWILD!, have received interest in certain contexts, d
Externí odkaz:
http://arxiv.org/abs/2102.09032
Autor:
Das, Sneha, Bäckström, Tom
Enhancement algorithms for wireless acoustics sensor networks~(WASNs) are indispensable with the increasing availability and usage of connected devices with microphones. Conventional spatial filtering approaches for enhancement in WASNs approximate q
Externí odkaz:
http://arxiv.org/abs/2011.03810
The COVID-19 outbreak disrupted different organizations, employees and students, who turned to teleconference applications to collaborate and socialize even during the quarantine. Thus, the demand of teleconferencing applications surged with mobile a
Externí odkaz:
http://arxiv.org/abs/2010.09488
Testing automotive mechatronic systems partly uses the software-in-the-loop approach, where systematically covering inputs of the system-under-test remains a major challenge. In current practice, there are two major techniques of input stimulation. O
Externí odkaz:
http://arxiv.org/abs/2002.06611