the safety of buried pipes under repeated load has been a challenging task in geotechnical engineering. in this paper artificial neural network and regression model for predicting the vertical deformation of high-density polyethylene (hdpe), small diameter flexible pipes buried in reinforced trenches, which were subjected to repeated loadings to simulate the heavy vehicle loads, are proposed. t...

We propose a novel deep supervised neural network for the task of action recognition in videos, which implicitly takes advantage of visual tracking and shares the robustness of both deep Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). In our method, a multi-branch model is proposed to suppress noise from background jitters. Specifically, we firstly extract multi-level dee...

Biologically inspired artificial neural networks have been widely used for machine learning tasks such as object recognition. Deep architectures, such as the Convolutional Neural Network, and the Deep Belief Network have recently been implemented successfully for object recognition tasks. We conduct experiments to test the hypothesis that certain primarily generative models such as the Deep Bel...

with the increase of the volume of information and the progress in technology, the deficiency of traditional algorithms for fast information retrieval becomes more clear. when large volumes of data are to be handled, the use of neural network as an artificial intelligent technique is a suitable method to increase the information retrieval speed. neural networks present a suitable representation...

Deep Learning has become most popular research topic because of its ability to learn from a huge amount of data. In recent research such as Atari 2600 games, they show that Deep Convolutional Neural Network (Deep CNN) can learn abstract information from pixel 2D data. After that, in VizDoom, we can also see the effect of pixel 3D data in learning to play games. But in all the cases above, the g...

Mini-batch based Stochastic Gradient Descent(SGD) has been widely used to train deep neural networks efficiently. In this paper, we design a general framework to automatically and adaptively select training data for SGD. The framework is based on neural networks and we call it Neural Data Filter (NDF). In Neural Data Filter, the whole training process of the original neural network is monitored...

This paper reviews recent studies in emerging directions of understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance in various tasks, the interpretability is always an Achilles' heel of deep neural networks. At present, deep neural networks obtain a h...

Object detection is a major challenge in computer vision, involving both object classification and object localization within a scene. While deep neural networks have been shown in recent years to yield very powerful techniques for tackling the challenge of object detection, one of the biggest challenges with enabling such object detection networks for widespread deployment on embedded devices ...

This paper summarizes SIATMMLAB’s contributions in SEACLEF2017 task [1]. We took part in three subtasks with advanced deep learning models. In Automatic Fish Identification and Species Recognition task, we exploited different frameworks to detect the proposal boxes of foreground fish, then fine-tuned a pre-trained neural network to classify the fish. In Automatic Frame-level Salmon Identificati...

We present in this paper our work on audio event classification for outdoor events. As the main classification method we employ a deep neural network (DNN) and compare this to other classification methods. We propose a novel improvement to the pre-training process of the network which is useful when training with Gaussian data. Our experimental results are based on an audio corpus extracted fro...