Three parallel algorithms for classical molecular dynamics are presented. The first assigns each processor a fixed subset of atoms; the second assigns each a fixed subset of inter-atomic forces to compute; the third assigns each a fixed spatial region. The algorithms are suitable for molecular dynamics models which can be difficult to parallelize efficiently—those with short-range forces where the neighbors of each atom change rapidly. They can be implemented on any distributed-memory parallel machine which allows for message-passing of data between independently executing processors. The algorithms are tested on a standard Lennard-Jones benchmark problem for system sizes ranging from 500 to 100,000,000 atoms on several parallel supercomputers--the nCUBE 2, Intel iPSC/860 and Paragon, and Cray T3D. Comparing the results to the fastest reported vectorized Cray Y-MP and C90 algorithm shows that the current generation of parallel machines is competitive with conventional vector supercomputers even for small problems. For large problems, the spatial algorithm achieves parallel efficiencies of 90% and a 1840-node Intel Paragon performs up to 165 faster than a single Cray C9O processor. Trade-offs between the three algorithms and guidelines for adapting them to more complex molecular dynamics simulations are also discussed.

Fast parallel algorithms for short-range molecular dynamics

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

We present a sensitivity analysis-based method for explaining prediction models that can be applied to any type of classification or regression model. Its advantage over existing general methods is that all subsets of input features are perturbed, so interactions and redundancies between features are taken into account. Furthermore, when explaining an additive model, the method is equivalent to commonly used additive model-specific methods. We illustrate the method's usefulness with examples from artificial and real-world data sets and an empirical analysis of running times. Results from a controlled experiment with 122 participants suggest that the method's explanations improved the participants' understanding of the model.

/pdf/explaining-prediction-models-and-individual-predictions-with-351ksyjxjq.pdf

Explaining prediction models and individual predictions with feature contributions

We present a general method for explaining individual predictions of classification models. The method is based on fundamental concepts from coalitional game theory and predictions are explained with contributions of individual feature values. We overcome the method's initial exponential time complexity with a sampling-based approximation. In the experimental part of the paper we use the developed method on models generated by several well-known machine learning algorithms on both synthetic and real-world data sets. The results demonstrate that the method is efficient and that the explanations are intuitive and useful.

/pdf/an-efficient-explanation-of-individual-classifications-using-4s1t0nr7u9.pdf

An Efficient Explanation of Individual Classifications using Game Theory

Bioinformatics — The Machine Learning Approach

An easy-to-follow introduction to support vector machines This book provides an in-depth, easy-to-follow introduction to support vector machines drawing only from minimal, carefully motivated technical and mathematical background material. It begins with a cohesive discussion of machine learning and goes on to cover: Knowledge discovery environments Describing data mathematically Linear decision surfaces and functions Perceptron learning Maximum margin classifiers Support vector machines Elements of statistical learning theory Multi-class classification Regression with support vector machines Novelty detection Complemented with hands-on exercises, algorithm descriptions, and data sets, Knowledge Discovery with Support Vector Machines is an invaluable textbook for advanced undergraduate and graduate courses. It is also an excellent tutorial on support vector machines for professionals who are pursuing research in machine learning and related areas.

Knowledge Discovery with Support Vector Machines

Background: Lyme borreliosis (LB) is the most commonly reported vector-borne disease in north temperate regions worldwide, affecting an estimated 300,000 people annually in the United States alone. The incidence of LB is correlated with human exposure to its vector, the blacklegged tick (Ixodes scapularis). To date, attempts to model tick encounter risk based on environmental parameters have been equivocal. Previous studies have not considered (1) the differences between relative humidity (RH) in leaf litter and at weather stations, (2) the RH threshold that affects nymphal blacklegged tick survival, and (3) the time required below the threshold to induce mortality. We clarify the association between environmental moisture and tick survival by presenting a significant relationship between the total number of tick adverse moisture events (TAMEs - calculated as microclimatic periods below a RH threshold) and tick abundance each year. Methods: We used a 14-year continuous statewide tick surveillance database and corresponding weather data from Rhode Island (RI), USA, to assess the effects of TAMEs on nymphal populations of I. scapularis. These TAMEs were defined as extended periods of time (>8 h below 82% RH in leaf litter). We fit a sigmoid curve comparing weather station data to those collected by loggers placed in tick habitats to estimate RH experienced by nymphal ticks, and compiled the number of historical TAMEs during the 14-year record. Results: The total number of TAMEs in June of each year was negatively related to total seasonal nymphal tick densities, suggesting that sub-threshold humidity episodes >8 h in duration naturally lowered nymphal blacklegged tick abundance. Furthermore, TAMEs were positively related to the ratio of tick abundance early in the season when compared to late season, suggesting that lower than average tick abundance for a given year resulted from tick mortality and not from other factors. Conclusions: Our results clarify the mechanism by which environmental moisture affects blacklegged tick populations, and offers the possibility to more accurately predict tick abundance and human LB incidence. We describe a method to forecast LB risk in endemic regions and identify the predictive role of microclimatic moisture conditions on tick encounter risk.

/pdf/adverse-moisture-events-predict-seasonal-abundance-of-lyme-49a5wdkjcx.pdf

Adverse moisture events predict seasonal abundance of Lyme disease vector ticks (Ixodes scapularis)

Introduction Classification models and in particular binary classification models are ubiquitous in many branches of science and business. Consider, for example, classification models in bioinformatics that classify catalytic protein structures as being in an active or inactive conformation. As an example from the field of medical informatics we might consider a classification model that, given the parameters of a tumor, will classify it as malignant or benign. Finally, a classification model in a bank might be used to tell the difference between a legal and a fraudulent transaction. this is accomplished by using metrics derived from the confusion matrix or contingency table. However, it has been recognized that (a) a scalar is a poor summary for the performance of a model in particular when deploying non-parametric models such as artificial neural networks or decision trees (Provost, Fawcett, & Kohavi, 1998) and (b) some performance metrics derived from the confusion matrix are sensitive to data anomalies such as class skew (Fawcett & Flach, 2005). Recently it has been observed that Receiver Operating Characteristic (ROC) curves visually convey the same information as the confusion matrix in a much more intuitive and robust fashion (Swets, Dawes, & Monahan, 2000). Here we take a look at model performance metrics derived from the confusion matrix. We highlight their shortcomings and illustrate how ROC curves can be deployed for model assessment in order to provide a much deeper and perhaps more intuitive analysis of the models. We also briefly address the problem of model selection.

/pdf/model-assessment-with-roc-curves-3ifva75ij9.pdf

Model Assessment with ROC Curves

The visualization of support vector machines in realistic settings is a difficult problem due to the high dimensionality of the typical datasets involved. However, such visualizations usually aid the understanding of the model and the underlying processes, especially in the biosciences. Here we propose a novel visualization technique of support vector machines based on unsupervised learning, specifically self-organizing maps. Conceptually, self-organizing maps can be thought of as neural networks that investigate a high-dimensional data space for clusters of data points and then project the clusters onto a two-dimensional map preserving the topologies of the original clusters as much as possible. This allows for the visualization of high-dimensional datasets together with their support vector models. With this technique we investigate a number of support vector machine visualization scenarios based on real world biomedical datasets.

/pdf/visualization-of-support-vector-machines-with-unsupervised-1bqx6xu0ow.pdf

Visualization of Support Vector Machines with Unsupervised Learning

Self-organizing maps are artificial neural networks designed for unsupervised machine learning. Here in this article, the authors introduce a new quality measure called the convergence index. The c...

Lutz Hamel

Papers

Knowledge Discovery with Support Vector Machines

Adverse moisture events predict seasonal abundance of Lyme disease vector ticks (Ixodes scapularis)

Model Assessment with ROC Curves

Visualization of Support Vector Machines with Unsupervised Learning

Self-Organizing Map Convergence