Mr. B. W. Tucker

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...

The Late Mr. John W. Davies

Consensus-halving via Theorems of Borsuk-ulam and Tucker Forest W. Simmons and Francis

Remembering Mr B.

In the accompanying translation and film, Gustav Störring describes the psychological profile of Mr. B. (Franz Breundl), a victim of carbon monoxide poisoning with a nearly complete short-term memory deficit. Störring diagnoses Mr. B. as lacking entirely the capacity to register or retain any information in consciousness for longer than two seconds. Here we introduce these historical documents,...