We present a new technique called “t-SNE” that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map. The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map. t-SNE is better than existing techniques at creating a single map that reveals structure at many different scales. This is particularly important for high-dimensional data that lie on several different, but related, low-dimensional manifolds, such as images of objects from multiple classes seen from multiple viewpoints. For visualizing the structure of very large datasets, we show how t-SNE can use random walks on neighborhood graphs to allow the implicit structure of all of the data to influence the way in which a subset of the data is displayed. We illustrate the performance of t-SNE on a wide variety of datasets and compare it with many other non-parametric visualization techniques, including Sammon mapping, Isomap, and Locally Linear Embedding. The visualizations produced by t-SNE are significantly better than those produced by the other techniques on almost all of the datasets.

/pdf/visualizing-data-using-t-sne-2w1n304iq0.pdf

Visualizing Data using t-SNE

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

https://axon.cs.byu.edu/~martinez/classes/678/Presentations/Yao.pdf

Extreme learning machine: Theory and applications

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.

By means of local neighborhood regression and time windows, the generative topographic mapping (GTM) allows to predict and visually inspect time series data. GTM itself, however, is fully unsupervised. In this contribution, we propose an extension of relevance learning to time series regression with GTM. This way, the metric automatically adapts according to the relevant time lags resulting in a sparser representation, improved accuracy, and smoother visualization of the data.

Relevance learning for time series inspection

In this paper, variable selection and variable scaling are used in order to select the best regressor for the problem of time series prediction. Direct prediction methodology is used instead of the classic recursive methodology. Least Squares Support Vector Machines (LS-SVM) are used in order to avoid local minimal in the training phase of the model. The global methodology is applied to the time series competition dataset.

Variable Scaling for Time Series Prediction

Underwater target detecting is an important technique for the development of the ocean engineering and exploration also a significant task of the ocean detecting. It plays a substantial role not only for the civil economy but also for the national security. The formation of the super-resolution underwater image is significant topic in ocean detecting field. In order to enhance the visual quality of images obtained by underwater imaging systems, super resolution (SR) reconstruction is introduced, including single-frame and multi-frame SR algorithms. Real-world images often contain singularities such as edges and high-frequency textured regions. As a result, these methods suffer from various edge-related visual artifacts such as ringing, aliasing, jagging, and blurring we mainly focus on super-resolution from single low resolution input image. The goal of single image super-resolution is to estimate a high resolution image from a low resolution input. In this paper, we propose a new high-quality and efficient single-image upscaling technique.

Underwater image super-resolution reconstruction with local self-similarity analysis and wavelet decomposition

Machine-learning disciplines including model design and data preprocessing are crucial in order to obtain a good performance in terms of accurate results and interpretability. However, they are not usually treated simultaneously and, when a model is evaluated, the origin and preprocessing of the data are ignored. Medicine and biomedical research provide a wide variety of problems where machine-learning can be very helpful in decision support, telemedicine, and the discovery of interactions.

These facts motivated the elaboration of this special issue; therefore, it is focused on methods and applications where machine learning could be applied holistically encompassing all stages to solve the problem. The papers included in the special issue go through the intersection between the medical field of application and theoretical models. For example, generalized estimating equations which are a common approach are compared against quadratic inference functions when applied to a lipid and glucose study. It is common in the field of medicine to be suspicious to predictions made by models, so it is interesting also to read another paper presenting the application of machine-learning techniques as a support decision tool that will not replace the expert judgment. This special issue not only considers the application of the models to improve the classification or prediction accuracy but also presents papers where the data are analysed properly. In medicine problems, it is quite common to have continuous and discrete variables in order to show how to deal with these situations; the paper entitled “Let continuous outcome variables remain continuous” shows how to apply a popular regression method without dichotomising the variables as this procedure could end up in the lost information.

We hope that the reading of this special issue will help medicine researchers to be aware of new methods and machine-learning techniques as well as to see how they could be applied. We also hope that the machine learning community can see here a wide variety of problems where the models and algorithms they create could be applied providing useful results.


Alberto Guillen

Amaury Lendasse

Guilherme Barreto

/pdf/data-preprocessing-and-model-design-for-medicine-problems-4fdae943ff.pdf

Amaury Lendasse

Papers

Relevance learning for time series inspection

Variable Scaling for Time Series Prediction

Underwater image super-resolution reconstruction with local self-similarity analysis and wavelet decomposition

Data Preprocessing and Model Design for Medicine Problems

ELMVIS: A nonlinear visualization technique using random permutations and ELMs