W. Pasierbek, B. Szlachta (red.), Seria: „Słowniki Społeczne”, Wydawnictwo Naukowe Akademii Ignatianum w Krakowie, Kraków 2020–2026. https://slownikispoleczne.ignatianum.edu.pl/

W 3 , b 3 ) ( W ′ 3 , b ′ 3 ) ( W ′ 2 , b ′ 2 ) ( W ′ 1 , b ′ 1 ) ( W ′ ′

In this paper, we present a deep neural network (DNN)-based acoustic scene classification framework. Two hierarchical learning methods are proposed to improve the DNN baseline performance by incorporating the hierarchical taxonomy information of environmental sounds. Firstly, the parameters of the DNN are initialized by the proposed hierarchical pre-training. Multi-level objective function is t...

W A B W A B Input Hidden Output

A modiication to neural network training algorithms is proposed which decorrelates certain weights within the network while minimising the mean squared error. The technique was developed to facilitate neural network interpretation in image processing problems, partly by allowing to initialise all network weights with one xed, low value. However, it can also be applied to classiica-tion tasks in...

w

w

B+W Filter Product Overview

W + W − Hadronic Decay Properties

Recent measurements of the properties of W + W − events produced in e + e − collisions at √ s ∼ 183 GeV at LEP are reviewed. The data are used to investigate the predicted effects of final state interactions, specifically " colour reconnection ". 1 Motivation Hadronic data in e + e − collisions can be characterised by event shape distributions and inclusive observables such as charged particle ...