Zobrazeno 1 - 10
of 524
pro vyhledávání: '"Mikael Skoglund"'
Publikováno v:
eLife, Vol 12 (2023)
According to the efficient coding hypothesis, sensory neurons are adapted to provide maximal information about the environment, given some biophysical constraints. In early visual areas, stimulus-induced modulations of neural activity (or tunings) ar
Externí odkaz:
https://doaj.org/article/737f212052d541a9a63d3403c408a1b4
Autor:
Andrew Karvonen, Vladimir Cvetkovic, Pawel Herman, Karl Johansson, Hedvig Kjellström, Marco Molinari, Mikael Skoglund
Publikováno v:
Urban Transformations, Vol 3, Iss 1, Pp 1-13 (2021)
Highlights The New Urban Science leverages digital tools and techniques to develop new knowledge that can inform urban development processes. Interdisciplinary and transdisciplinary approaches are critical to expanding and enhancing digital modes of
Externí odkaz:
https://doaj.org/article/e110835c225e454da03b5428409edb7d
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2020, Iss 1, Pp 1-19 (2020)
Abstract We design a rectified linear unit-based multilayer neural network by mapping the feature vectors to a higher dimensional space in every layer. We design the weight matrices in every layer to ensure a reduction of the training cost as the num
Externí odkaz:
https://doaj.org/article/6d243ccdf0b54f84a5b0380d1b9b98fc
Autor:
Ming Xiao, Mikael Skoglund
Publikováno v:
Entropy, Vol 24, Iss 9, p 1284 (2022)
This article aims to give a comprehensive and rigorous review of the principles and recent development of coding for large-scale distributed machine learning (DML). With increasing data volumes and the pervasive deployment of sensors and computing ma
Externí odkaz:
https://doaj.org/article/84ec5ae4ef3244c1a01a5e2ae4cfa176
Publikováno v:
Entropy, Vol 24, Iss 2, p 306 (2022)
The distance that compares the difference between two probability distributions plays a fundamental role in statistics and machine learning. Optimal transport (OT) theory provides a theoretical framework to study such distances. Recent advances in OT
Externí odkaz:
https://doaj.org/article/67308c4ee3bf49d3ae5ef47a242f1657
Publikováno v:
Entropy, Vol 23, Iss 6, p 641 (2021)
Novel approaches to estimate information measures using neural networks are well-celebrated in recent years both in the information theory and machine learning communities. These neural-based estimators are shown to converge to the true values when e
Externí odkaz:
https://doaj.org/article/d46dbd3fbb6c4115960155cadcd339cc
Publikováno v:
Entropy, Vol 22, Iss 8, p 842 (2020)
In this paper, we derive lower and upper bounds on the OPTA of a two-user multi-input multi-output (MIMO) causal encoding and causal decoding problem. Each user’s source model is described by a multidimensional Markov source driven by additive i.i.
Externí odkaz:
https://doaj.org/article/c6a441dd4b2e4c1a993a879810023a54
Publikováno v:
Entropy, Vol 22, Iss 1, p 98 (2020)
The information bottleneck (IB) problem tackles the issue of obtaining relevant compressed representations T of some random variable X for the task of predicting Y. It is defined as a constrained optimization problem that maximizes the information th
Externí odkaz:
https://doaj.org/article/cea58bf84bc54ca3afc953fc545b55b6
Publikováno v:
EAI Endorsed Transactions on Ambient Systems, Vol 2, Iss 7, Pp 1-7 (2015)
In this paper we study cognitive radio networks with secrecy constraints on the primary transmission. In particular we consider several transmission schemes for the secondary transmitter, namely interference neutralization (IN) and cooperative jammin
Externí odkaz:
https://doaj.org/article/59f32ab90fe5462d85c81c1dc79aae9e
Publikováno v:
Journal of Sensor and Actuator Networks, Vol 3, Iss 1, Pp 1-25 (2013)
Compressed sensing is a thriving research field covering a class of problems where a large sparse signal is reconstructed from a few random measurements. In the presence of several sensor nodes measuring correlated sparse signals, improvements in ter
Externí odkaz:
https://doaj.org/article/262fac493e3649389f1d810fb4474a0e