Automatic extraction of distinctive features from a visual information stream is challenging due to the large amount of information contained in most image data. In recent years deepneuralnetworks (DNNs) have gained...
详细信息
Automatic extraction of distinctive features from a visual information stream is challenging due to the large amount of information contained in most image data. In recent years deepneuralnetworks (DNNs) have gained outstanding popularity for solving visual information processing tasks. This study reports novel contributions, including a new DNN architecture and training method, which increase the fidelity of DNN-based representations to encodings extracted by visual processing neurons. Our local receptive field constrained DNNs (LRF-DNNs) are pre-trained with a modified restricted Boltzmann machine, the LRF-RBM, which utilizes biologically inspired Gaussian receptive field constraints to encourage the emergence of local features. Moreover, we propose a method for concurrently finding advantageous receptive field centers, while training the LRF-RBM. By utilizing LRF-RBMs with gradually increasing receptive field sizes on each layer, our LRF-DNN learns features of increasing complexity and demonstrates hierarchical part-based compositionality. We show superior face completion and reconstruction results on the challenging LFW face dataset. (C) 2016 Elsevier Inc. All rights reserved.
Modern air quality monitoring systems are characterised by high complexity and costs. The expensive embedded units such as sensor arrays, processors, power blocks, displays and communication units make them less appro...
详细信息
ISBN:
(数字)9783030239763
ISBN:
(纸本)9783030239763;9783030239756
Modern air quality monitoring systems are characterised by high complexity and costs. The expensive embedded units such as sensor arrays, processors, power blocks, displays and communication units make them less appropriate for small indoor spaces. In this paper we demonstrate that two widely available, in private houses, sensors (for Humidity and Temperature) are promising alternative, to the expensive indoor air quality solutions, provided with intelligent data processing tools. Our findings suggest that neuralnetwork based data analytics system can learn to discriminate unusual indoor gases from normal home air components based only on temperature and humidity measurements.
暂无评论