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 Practical Machine Learning Tools and Techniques

http://www.csun.edu/~andrzej/COMP529-S05/papers/Mesh%20Networks%20Survey.pdf

Wireless mesh networks: a survey

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

The Arizona State University (ASU) - Dublin City University (DCU) International Research Experiences for Students (IRES) project is a summer workforce development program that embeds students in machine learning and sensor research. This collaborative IRES program, funded by the National Science Foundation (NSF), engages faculty mentors from the Sensor, Signal, Information Processing (SenSIP) Center at ASU, and the Insight SFI Research Centre for Data Analytics and Biodesign Europe at DCU to train students in sensor design, analytics, and machine learning algorithm development. Sensor and machine learning research addresses engineering and computing problems in health care and other related applications. IRES participants are tasked with studying hardware, algorithms and software for various tasks including activity detection, gait modeling, imaging, hemochromatosis prediction, and health care analytics. Crosscutting efforts include training in international research presentations, research documentation and building awareness of international policies and standards. The program includes weekly research updates by the students, participation in workshops and continued engagement after the summer experience. This paper describes the various components of IRES sensor and machine learning research through ongoing center projects at ASU and DCU.

The ASU-DCU International Research and Workforce Development Program on Sensors and Machine Learning

We present in this paper a method to compare scene classification accuracy of C-band Synthetic aperture radar (SAR) and optical images utilizing both classical and quantum computing algorithms. This REU study uses data from the Sentinel satellite. The dataset contains (i) synthetic aperture radar images collected from the Sentinel-1 satellite and (ii) optical images for the same area as the SAR images collected from the Sentinel-2 satellite. We examine classical neural networks to classify four classes of images. We then explore Quantum Convolutional Neural Networks and deep learning techniques in terms of their training and classification performance. A hybrid Quantum-classical model that is trained on the Sentinel1-2 dataset is proposed, and its performance is then compared against the classical model in terms of classification accuracy.

Quantum Machine Learning for Optical and SAR Classification

Raja Ayyanar received the M.S. degree from the Indian Institute of Science, Bangalore, India, and the Ph.D. degree from the University of Minnesota, Minneapolis. He is presently an Associate Professor at the Arizona State University, Tempe. His current research activities are in the area of power electronics for renewable energy integration, dc-dc converters, power management, fully modular power system architecture and new control and pulsewidth modulation techniques. He received an ONR Young Investigator Award in 2005.

Designing Online Laboratories for Power Electronics Courses using J-DSP Software

With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate predictions but also do not generalize to data regimes where the training data provide no meaningful evidence. Existing approaches for ensuring the distribution of model predictions to be similar to that of the true distribution rely on explicit uncertainty estimators that are inherently hard to calibrate. In this paper, we propose to train a loss estimator alongside the predictive model, using a contrastive training objective, to directly estimate the prediction uncertainties. Interestingly, we find that, in addition to producing well-calibrated uncertainties, this approach improves the generalization behavior of the predictor. Using a dermatology use-case, we show the impact of loss estimators on model generalization, in terms of both its fidelity on in-distribution data and its ability to detect out of distribution samples or new classes unseen during training.

Loss Estimators Improve Model Generalization.

The performance of adaptive FIR algorithms in the presence of bounded disturbances, in particular, algorithms based on gradient mean squared error (MSE) estimators, gradient estimators with dead-zone thresholds, and set membership estimators, is examined. A simple example of the bursting phenomenon is given, and the algorithms and their properties are described. Analytical results on the performance of these estimators are also given. An algorithm that provides both MSE and instantaneous maximum amplitude error (in the limsup sense) performance guarantees is proposed. >

Andreas Spanias

Papers

The ASU-DCU International Research and Workforce Development Program on Sensors and Machine Learning

Quantum Machine Learning for Optical and SAR Classification

Designing Online Laboratories for Power Electronics Courses using J-DSP Software

Loss Estimators Improve Model Generalization.

Adaptive FIR filtering based on bounded error constraints