Deep Learning Architectures and Applications (딥러닝의 모형과 응용사례)
-
- 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.
This study described the utilization of ChatGPT in teaching and students' learning processes for the course "Introductory Mathematics for Artificial Intelligence (Math4AI)" at 'S' University. We developed a customized ChatGPT and presented a learning model in which students supplement their knowledge of the topic at hand by utilizing this model. More specifically, first, students learn the concepts and questions of the course textbook by themselves. Then, for any question they are unsure of, students may submit any questions (keywords or open problem numbers from the textbook) to our own ChatGPT at https://math4ai.solgitmath.com/ to get help. Notably, we optimized ChatGPT and minimized inaccurate information by fully utilizing various types of data related to the subject, such as textbooks, labs, discussion records, and codes at http://matrix.skku.ac.kr/Math4AI-ChatGPT/. In this model, when students have questions while studying the textbook by themselves, they can ask mathematical concepts, keywords, theorems, examples, and problems in natural language through the ChatGPT interface. Our customized ChatGPT then provides the relevant terms, concepts, and sample answers based on previous students' discussions and/or samples of Python or R code that have been used in the discussion. Furthermore, by providing students with real-time, optimized advice based on their level, we can provide personalized education not only for the Math4AI course, but also for any other courses in college math education. The present study, which incorporates our ChatGPT model into the teaching and learning process in the course, shows promising applicability of AI technology to other college math courses (for instance, calculus, linear algebra, discrete mathematics, engineering mathematics, and basic statistics) and in K-12 math education as well as the Lifespan Learning and Continuing Education.
People are nowadays creating a tremendous amount of data on Social Network Service (SNS). In particular, the incorporation of SNS into mobile devices has resulted in massive amounts of data generation, thereby greatly influencing society. This is an unmatched phenomenon in history, and now we live in the Age of Big Data. SNS Data is defined as a condition of Big Data where the amount of data (volume), data input and output speeds (velocity), and the variety of data types (variety) are satisfied. If someone intends to discover the trend of an issue in SNS Big Data, this information can be used as a new important source for the creation of new values because this information covers the whole of society. In this study, a Twitter Issue Tracking System (TITS) is designed and established to meet the needs of analyzing SNS Big Data. TITS extracts issues from Twitter texts and visualizes them on the web. The proposed system provides the following four functions: (1) Provide the topic keyword set that corresponds to daily ranking; (2) Visualize the daily time series graph of a topic for the duration of a month; (3) Provide the importance of a topic through a treemap based on the score system and frequency; (4) Visualize the daily time-series graph of keywords by searching the keyword; The present study analyzes the Big Data generated by SNS in real time. SNS Big Data analysis requires various natural language processing techniques, including the removal of stop words, and noun extraction for processing various unrefined forms of unstructured data. In addition, such analysis requires the latest big data technology to process rapidly a large amount of real-time data, such as the Hadoop distributed system or NoSQL, which is an alternative to relational database. We built TITS based on Hadoop to optimize the processing of big data because Hadoop is designed to scale up from single node computing to thousands of machines. Furthermore, we use MongoDB, which is classified as a NoSQL database. In addition, MongoDB is an open source platform, document-oriented database that provides high performance, high availability, and automatic scaling. Unlike existing relational database, there are no schema or tables with MongoDB, and its most important goal is that of data accessibility and data processing performance. In the Age of Big Data, the visualization of Big Data is more attractive to the Big Data community because it helps analysts to examine such data easily and clearly. Therefore, TITS uses the d3.js library as a visualization tool. This library is designed for the purpose of creating Data Driven Documents that bind document object model (DOM) and any data; the interaction between data is easy and useful for managing real-time data stream with smooth animation. In addition, TITS uses a bootstrap made of pre-configured plug-in style sheets and JavaScript libraries to build a web system. The TITS Graphical User Interface (GUI) is designed using these libraries, and it is capable of detecting issues on Twitter in an easy and intuitive manner. The proposed work demonstrates the superiority of our issue detection techniques by matching detected issues with corresponding online news articles. The contributions of the present study are threefold. First, we suggest an alternative approach to real-time big data analysis, which has become an extremely important issue. Second, we apply a topic modeling technique that is used in various research areas, including Library and Information Science (LIS). Based on this, we can confirm the utility of storytelling and time series analysis. Third, we develop a web-based system, and make the system available for the real-time discovery of topics. The present study conducted experiments with nearly 150 million tweets in Korea during March 2013.
The wall shear stress in the vicinity of end-to end anastomoses under steady flow conditions was measured using a flush-mounted hot-film anemometer(FMHFA) probe. The experimental measurements were in good agreement with numerical results except in flow with low Reynolds numbers. The wall shear stress increased proximal to the anastomosis in flow from the Penrose tubing (simulating an artery) to the PTFE: graft. In flow from the PTFE graft to the Penrose tubing, low wall shear stress was observed distal to the anastomosis. Abnormal distributions of wall shear stress in the vicinity of the anastomosis, resulting from the compliance mismatch between the graft and the host artery, might be an important factor of ANFH formation and the graft failure. The present study suggests a correlation between regions of the low wall shear stress and the development of anastomotic neointimal fibrous hyperplasia(ANPH) in end-to-end anastomoses. 30523 T00401030523 ^x Air pressure decay(APD) rate and ultrafiltration rate(UFR) tests were performed on new and saline rinsed dialyzers as well as those roused in patients several times. C-DAK 4000 (Cordis Dow) and CF IS-11 (Baxter Travenol) reused dialyzers obtained from the dialysis clinic were used in the present study. The new dialyzers exhibited a relatively flat APD, whereas saline rinsed and reused dialyzers showed considerable amount of decay. C-DAH dialyzers had a larger APD(11.70
The wall shear stress in the vicinity of end-to end anastomoses under steady flow conditions was measured using a flush-mounted hot-film anemometer(FMHFA) probe. The experimental measurements were in good agreement with numerical results except in flow with low Reynolds numbers. The wall shear stress increased proximal to the anastomosis in flow from the Penrose tubing (simulating an artery) to the PTFE: graft. In flow from the PTFE graft to the Penrose tubing, low wall shear stress was observed distal to the anastomosis. Abnormal distributions of wall shear stress in the vicinity of the anastomosis, resulting from the compliance mismatch between the graft and the host artery, might be an important factor of ANFH formation and the graft failure. The present study suggests a correlation between regions of the low wall shear stress and the development of anastomotic neointimal fibrous hyperplasia(ANPH) in end-to-end anastomoses. 30523 T00401030523 ^x Air pressure decay(APD) rate and ultrafiltration rate(UFR) tests were performed on new and saline rinsed dialyzers as well as those roused in patients several times. C-DAK 4000 (Cordis Dow) and CF IS-11 (Baxter Travenol) reused dialyzers obtained from the dialysis clinic were used in the present study. The new dialyzers exhibited a relatively flat APD, whereas saline rinsed and reused dialyzers showed considerable amount of decay. C-DAH dialyzers had a larger APD(11.70