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.

This concept paper highlights a recently opened opportunity for large scale analytical algorithms to be trained directly on edge devices. Such approach is a response to the arising need of processing data generated by natural person (a human being), also known as personal data. Spiking Neural networks are the core method behind it: suitable for a low latency energy-constrained hardware, enabling local training or re-training, while not taking advantage of scalability available in the Cloud.

Spiking Networks for Improved Cognitive Abilities of Edge Computing Devices

In this paper, a novel weighted median filter model has been put forward with saliency detection for underwater image denoising. Saliency detection is first taken to only optionally highlight and prominent the salient region in the underwater images. One weighted median filter is further proposed to greatly accelerate the image denoising speed. It has been shown in our simulation experiments that the proposed method not only can provide better performance of suppressing noises and preserving the detailed features in underwater images, but also the running time can be largely shortened.

A rapid weighted median filter based on saliency region for underwater image denoising

RESUME. L’existence de valeurs manquantes dans les series temporelles est un probleme recurrent lors de l’utilisation de modeles financiers. En effet, de tels modeles requierent que les bases soient cylindrees et completes. De plus, de nombreuses bases de donnees financieres contiennent des valeurs manquantes. Ce papier presente une nouvelle technique pour le recouvrement des valeurs manquantes. Cette methode utilise deux techniques de projection : une non-lineaire (Cartes de Kohonen) et une lineaire (Fonction Orthogonale Empirique). La methodologie globale presentee combine les avantages des deux methodes pour obtenir des candidats aux valeurs manquantes. La methode est appliquee a deux bases de donnees financieres.

A Nonlinear Approach for the Determination of Missing Values in Temporal Databases

Time Series Benchmarking Competition: The CATS Benchmark

The bankruptcies of companies have been predicted with numerous methods. In this paper, the ensemble of Locally Linear model is compared to Linear Discriminant Analysis, Least Squares Support Vector Machines and Optimally Pruned Extreme Learning Machines. To create the ensemble, diffrerent basis for the locally linear models as well as different combinations of variables are used in order to obtain enough diversity between the models. The obtained models are combined into the final model by solving a least-squares nonnegative constraints problem. The model is tested on a Polish bankruptcy data set and the results discussed also from the point of view of importance of the variables.

Amaury Lendasse

Papers

Spiking Networks for Improved Cognitive Abilities of Edge Computing Devices

A rapid weighted median filter based on saliency region for underwater image denoising

A Nonlinear Approach for the Determination of Missing Values in Temporal Databases

Time Series Benchmarking Competition: The CATS Benchmark

Ensembles of Locally Linear Models: Application to Bankruptcy Prediction.