Confidence bounds of petrophysical predictions from conventional neural networks
نویسندگان
چکیده
منابع مشابه
Confidence bounds of petrophysical predictions from conventional neural networks
Neural networks are powerful tools for solving the complex regression problems which abound in geosciences. Estimation of prediction confidence from neural networks is an important area. Many procedures are available to date, but it is often tedious for practitioners to implement such procedures without significant modification of the existing learning algorithms. In many cases, the procedures ...
متن کاملNmr Petrophysical Predictions on Digitized Core Images
NMR is a popular logging technique used to estimate pore size information, formation permeability, wettability and irreducible water saturation. Quantitative interpretation of NMR data is based on a set of fundamental assumptions (e.g., pore isolation and fast diffusion). These assumptions establish the quantitative link between NMR response and petrophysical predictions. While there is a need ...
متن کاملAssigning Confidence Intervals to Neural Network Predictions
Abstract This report reviews three possible approaches to the assignment of confidence intervals to feed-forward neural networks, namely, bootstrap estimation, maximum likelihood estimation, and Bayesian statistics. The report concludes with a proposal for mixture modelling via Markov Chain Monte Carlo sampling to enable non-Gaussian variances to be modelled without introducing the bias caused ...
متن کاملRapid Physical Predictions from Convolutional Neural Networks
Every day we use intuitive reasoning to make and update predictions about the world. For instance, when playing soccer we must predict the trajectories of the ball but also update those predictions in light of new information. But these predictions must also be rapid – if we turn to see a soccer ball flying at us, we must quickly decide whether or not to duck. What prediction mechanism would al...
متن کاملSupplementary Material for Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
As we wrote in the paper: “One question is whether different DNNs learn the same features for each class, or whether each trained DNN learns different discriminative features. One way to shed light on that question is to see if images that fool one DNN also fool another. To test that, we evolved CPPN-encoded images with one DNN (DNNA) and then input them to another DNN (DNNB), where DNNA and DN...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Geoscience and Remote Sensing
سال: 2002
ISSN: 0196-2892
DOI: 10.1109/tgrs.2002.800278