Share by La Forge
Contact us

6 articles

Machine Learning for Mapping Groundwater Salinity with Oil Well Log Data - NASA/ADS

2019-11-09 ui.adsabs.harvard.edu 21

An oil field may have thousands of wells with detailed petrophysical logs, and far fewer direct measurements of groundwater salinity. Can the former be used to extrapolate the latter into a detailed map of groundwater salinity? California Senate Bill 4, with its requirement to identify Underground Sources of Drinking Water, makes this a question worth answering. A well-known obstacle is that the basic petrophysical equations describe ideal scenarios ("clean wet sand") and even these equations co[...]
Legal Risks of Adversarial Machine Learning Research - NASA/ADS

2020-08-01 ui.adsabs.harvard.edu 19

Adversarial Machine Learning is booming with ML researchers increasingly targeting commercial ML systems such as those used in Facebook, Tesla, Microsoft, IBM, Google to demonstrate vulnerabilities. In this paper, we ask, "What are the potential legal risks to adversarial ML researchers when they attack ML systems?" Studying or testing the security of any operational system potentially runs afoul the Computer Fraud and Abuse Act (CFAA), the primary United States federal statute that creates liab[...]
A Review of Object Detection Models based on Convolutional Neural Network - NASA/ADS

2019-11-10 ui.adsabs.harvard.edu 14

Convolutional Neural Network (CNN) has become the state-of-the-art for object detection in image task. In this chapter, we have explained different state-of-the-art CNN based object detection models. We have made this review with categorization those detection models according to two different approaches: two-stage approach and one-stage approach. Through this chapter, it has shown advancements in object detection models from R-CNN to latest RefineDet. It has also discussed the model description[...]
A Novel Adaptive Kernel for the RBF Neural Networks - NASA/ADS

2020-03-14 ui.adsabs.harvard.edu 13

In this paper, we propose a novel adaptive kernel for the radial basis function (RBF) neural networks. The proposed kernel adaptively fuses the Euclidean and cosine distance measures to exploit the reciprocating properties of the two. The proposed framework dynamically adapts the weights of the participating kernels using the gradient descent method thereby alleviating the need for predetermined weights. The proposed method is shown to outperform the manual fusion of the kernels on three major p[...]
Planning chemical syntheses with deep neural networks and symbolic AI - NASA/ADS

2019-11-07 ui.adsabs.harvard.edu 12

To plan the syntheses of small organic molecules, chemists use retrosynthesis, a problem-solving technique in which target molecules are recursively transformed into increasingly simpler precursors. Computer-aided retrosynthesis would be a valuable tool but at present it is slow and provides results of unsatisfactory quality. Here we use Monte Carlo tree search and symbolic artificial intelligence (AI) to discover retrosynthetic routes. We combined Monte Carlo tree search with an expansion polic[...]
Deep Learning Based Solar Flare Forecasting Model. I. Results for Line-of-sight Magnetograms - NASA/ADS

2019-11-12 ui.adsabs.harvard.edu 6

Solar flares originate from the release of the energy stored in the magnetic field of solar active regions, the triggering mechanism for these flares, however, remains unknown. For this reason, the conventional solar flare forecast is essentially based on the statistic relationship between solar flares and measures extracted from observational data. In the current work, the deep learning method is applied to set up the solar flare forecasting model, in which forecasting patterns can be learned f[...]