Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining - Concepts and Techniques.

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Network intrusion detection systems (NIDSs) play a crucial role in defending computer networks. However, there are concerns regarding the feasibility and sustainability of current approaches when faced with the demands of modern networks. More specifically, these concerns relate to the increasing levels of required human interaction and the decreasing levels of detection accuracy. This paper presents a novel deep learning technique for intrusion detection, which addresses these concerns. We detail our proposed nonsymmetric deep autoencoder (NDAE) for unsupervised feature learning. Furthermore, we also propose our novel deep learning classification model constructed using stacked NDAEs. Our proposed classifier has been implemented in graphics processing unit (GPU)-enabled TensorFlow and evaluated using the benchmark KDD Cup ’99 and NSL-KDD datasets. Promising results have been obtained from our model thus far, demonstrating improvements over existing approaches and the strong potential for use in modern NIDSs.

/pdf/a-deep-learning-approach-to-network-intrusion-detection-n63kpq7big.pdf

A Deep Learning Approach to Network Intrusion Detection

Each learner has different preferences and needs. Therefore, it is very crucial to provide the different styles of learners with different learning environments that are more preferred and more efficient to them. This paper reports a study of the intelligent learning environment where the learner's preferences are diagnosed, and then user interfaces are customized in an adaptive manner to accommodate the preferences. A learning system with a specific interface has been devised based on the learning-style model by Felder & Silverman, so that different learner preferences are revealed through user interactions with the system. Using this interface, learning styles are diagnosed from learner behavior patterns on the interface using Decision Tree and Hidden Markov Model approaches.

Learning styles diagnosis based on user interface behaviors for the customization of learning interfaces in an intelligent tutoring system

As the physical design of semiconductors continues to shrink, the lithography process is becoming more sensitive to layout design. Identifying lithography hotspots (HSs) in the layout design stage appears to be more and more crucial for fast semiconductor development. In this direction, we propose an accurate HS detection method using convolutional neural networks. Our approach produces more accurate detection performance (95.5% recall and 22.2% precision) compared to previous approaches. In spite of the use of deep convolutional neural networks, our method achieves a fast detection time of 0.72  h/mm2. In order to quickly and accurately detect HSs, we not only utilize the nature of convolutional-neural networks but also make additional technical efforts to improve the performance of our framework, including inspection region reduction, data augmentation, DBSCAN clustering, modified batch normalization, and fast image scanning. To the best of our knowledge, our approach is the first CNN-based lithography HS detection.

Jee-Hyong Lee

Papers

Learning styles diagnosis based on user interface behaviors for the customization of learning interfaces in an intelligent tutoring system

Accurate lithography hotspot detection using deep convolutional neural networks

Deep Neural Network Self-training Based on Unsupervised Learning and Dropout

Autonomic machine learning platform

An approach for multi-label classification by directed acyclic graph with label correlation maximization