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

Data Mining Practical Machine Learning Tools and Techniques

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

Data analysis plays an indispensable role for understanding various phenomena. Cluster analysis, primitive exploration with little or no prior knowledge, consists of research developed across a wide variety of communities. The diversity, on one hand, equips us with many tools. On the other hand, the profusion of options causes confusion. We survey clustering algorithms for data sets appearing in statistics, computer science, and machine learning, and illustrate their applications in some benchmark data sets, the traveling salesman problem, and bioinformatics, a new field attracting intensive efforts. Several tightly related topics, proximity measure, and cluster validation, are also discussed.

/pdf/survey-of-clustering-algorithms-6zezqhbjyo.pdf

Survey of clustering algorithms

http://masou-keshtkar.persiangig.com/document/sdarticle.pdf

GSA: A Gravitational Search Algorithm

In the past few decades major advances in the fields of molecular biology and genomic technology have led to an explosive growth in the biological information generated by the scientific community. Bioinformatics has evolved as an emerging research direction in response to this deluge of information. It is viewed as the use of computational methods to make biological discoveries, and is almost synonymous with computational biology.

Computational Biology and Bioinformatics

Catastrophic forgetting of previously acquired knowledge is a major setback suffered by the neural networks (NNs) when these are trained on tasks in sequential fashion. The NN variants, including the deep network models, as commonly used in remote sensing data prediction are also not free from this limitation. The issue becomes more prominent when the prediction is performed over data collected from spatial zones with a large degree of subregional variations or heterogeneity. In order to tackle this problem, in this article, we propose a multilayered adaptive recurrent incremental network (MARINE) model, offering a spatial heterogeneity-aware self-adaptation scheme that resolves the catastrophic forgetting issue in an autonomous manner. Typically, the proposed MARINE is equipped with an intrinsic mechanism of clustering the spatial subregions as per their heterogeneity levels and auto-constructing the recurrent network layers in an ensemble fashion so that the knowledge acquired about one group of heterogeneity level does not overwrite that acquired about other groups. With respect to spatio-temporal prediction of normalized difference vegetation index (NDVI) time series, as derived from MODIS Terra satellite remote sensing imagery, we demonstrate that our proposed MARINE achieves competitive results when compared with the state-of-the-arts. More significantly, in the presence of higher degree of spatial heterogeneity, MARINE outperforms others by better avoiding the catastrophic forgetting issue.

A Multilayered Adaptive Recurrent Incremental Network Model for Heterogeneity-Aware Prediction of Derived Remote Sensing Image Time Series

In this article, we construct a random number generator using a one dimensional, nonuniform 4-Neighborhood Cellular Automata (4NCA). A probabilistic analysis of CA rules has been done to select the appropriate rules for 4NCA random number generator (RNG). A comparison is made between the pseudo random patterns generated by using the proposed CA RNGs with those obtained using a recent Cellular Programming (CP) evolved CA RNGs. The results show that our approach outperforms CP both in terms of average time taken to evolve CA rules and in terms of quality of pseudo random patterns generated. The proposed approach is also shown to be better than the common generators such as Shift Register, Congruential Generator and Lagged Fibonacci Generator.

/pdf/pseudorandom-pattern-generation-by-a-4-neighborhood-cellular-8xxq1k318t.pdf

Pseudorandom Pattern Generation by a 4-Neighborhood Cellular Automata Based on a Probabilistic Analysis

A novel multi-objective evolutionary algorithm (MOEA), called multi-objective genetic algorithm with relative distance (MOGARD) is described. A novel relative distance parameter that ensures convergence to the Pareto optimal front and a nearest neighbour based method for maintaining diversity in the non-dominated set is used. Two novel performance measures are formulated to estimate the performance of the MOEAs. A penalty based constraint handling concept is introduced in MOGARD, for handling constraints. Experimental results demonstrate the superiority of MOGARD on several test problems, as compared to other recent and well known algorithms

A Multi-objective Genetic Algorithm with Relative Distance: Method, Performance Measures and Constraint Handling

Computational approaches are widely studied for zero-cost human-based building retrofit planning while satisfying occupants’ comfort demands. Previous studies focus on generating Pareto-optimal schedules of occupant actions (opening/closing of doors/windows) by minimizing thermal and air quality discomfort. However, these search procedures overlook the possibility of multiple action schedules for similar comfort trade-offs. In the absence of expert knowledge, schedule selection is based on the subjective preference of comfort quantifiers. Motivating occupants to change their daily (recorded) schedule to an optimal plan for the desired impact of actions can be time-consuming. To simplify this process to some extent, a Pareto-optimal schedule can be recommended which closely resembles occupants’ daily schedule. For achieving this goal, a multi-modal multi-objective evolutionary algorithm is integrated with a binary-coded genetic algorithm (referred to as GA-TriM) to address the concerned optimization problem. From the set of Pareto-optimal schedules of actions, the subset of those schedules is obtained, which have minimum changes from occupants’ daily schedule. The schedule from this subset with minimum net discomfort is recommended as the best solution to the concerned problem. Further analysis is done by comparing the proposed schedule selection strategy with the existing approaches.

Sanghamitra Bandyopadhyay

Papers

Computational Biology and Bioinformatics

A Multilayered Adaptive Recurrent Incremental Network Model for Heterogeneity-Aware Prediction of Derived Remote Sensing Image Time Series

Pseudorandom Pattern Generation by a 4-Neighborhood Cellular Automata Based on a Probabilistic Analysis

A Multi-objective Genetic Algorithm with Relative Distance: Method, Performance Measures and Constraint Handling

Occupant Actions Selection Strategies Based on Pareto-Optimal Schedules and Daily Schedule for Energy Management in Buildings