A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network. Especially, recurrent neural network and deep convolutional neural network have been applied in ASR successfully. Given the arising problem of training speed, w...

We experimentally demonstrate a camera whose primary optic is cannula (diameter=0.22mm and length=12.5mm) that acts lightpipe transporting light intensity from an object plane (35cm away) to its opposite end. Deep neural networks (DNNs) are used reconstruct color grayscale images with field of view 180 angular resolution ~0.40. When trained on depth information, the DNN can create maps. Finally...

In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural network with four recurrent neural networks that sweep horizontally and vertically in both directions across the image. We evaluate the proposed ReNet on thre...

This paper deals with the effect of fiber aspect ratio of steel fibers on shear strength of steel fiber reinforced concrete deep beams loaded with shear span to depth ratio less than two using the artificial neural network technique. The network model predicts reasonably good results when compared with the equation proposed by previous researchers. The parametric study invol...

Deep learning using multi-layer neural networks (NNs) architecture manifests superb power in modern machine learning systems. The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it is possible to simplify the NN during training process to achieve a reasonable performance within an acceptable computational time. We presented a novel appro...

Recently, the deep neural network (derived from the artificial neural network) has attracted many researchers’ attention by its outstanding performance. However, since this network requires high-performance GPUs and large storage, it is very hard to use it on individual devices. In order to improve the deep neural network, many trials have been made by refining the network structure or training...

We implement two deep architectures for the acousticarticulatory inversion mapping problem: a deep neural network and a deep trajectory mixture density network. We find that in both cases, deep architectures produce more accurate predictions than shallow architectures and that this is due to the higher expressive capability of a deep model and not a consequence of adding more adjustable paramet...