• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of Korea Spatial Information System Society
• /
• v.6 no.1 s.11
• /
• pp.73-85
• /
• 2004

Recently, as the growth of the wireless Internet, PDA and HPC, the focus of research and development related with GIS(Geographic Information System) has been changed to the Real-Time Mobile GIS to service LBS. To offer LBS efficiently, there must be the Real-Time GIS platform that can deal with dynamic status of moving objects and a location index which can deal with the characteristics of location data. Location data can use the same data type(e.g., point) of GIS, but the management of location data is very different. Therefore, in this paper, we studied the Real-Time Mobile GIS using the HBR-tree to manage mass of location data efficiently. The Real-Time Mobile GIS which is developed in this paper consists of the HBR-tree and the Real-Time GIS Platform HBR-tree. we proposed in this paper, is a combined index type of the R-tree and the spatial hash Although location data are updated frequently, update operations are done within the same hash table in the HBR-tree, so it costs less than other tree-based indexes Since the HBR-tree uses the same search mechanism of the R-tree, it is possible to search location data quickly. The Real-Time GIS platform consists of a Real-Time GIS engine that is extended from a main memory database system. a middleware which can transfer spatial, aspatial data to clients and receive location data from clients, and a mobile client which operates on the mobile devices. Especially, this paper described the performance evaluation conducted with practical tests if the HBR-tree and the Real-Time GIS engine respectively.