N
Nicolás Cruz
Researcher at University of Chile
Publications - 9
Citations - 122
Nicolás Cruz is an academic researcher from University of Chile. The author has contributed to research in topics: Robot & Prediction interval. The author has an hindex of 6, co-authored 8 publications receiving 87 citations.
Papers
More filters
Journal ArticleDOI
Prediction interval methodology based on fuzzy numbers and its extension to fuzzy systems and neural networks
TL;DR: Fuzzy and neural network prediction interval models are developed based on fuzzy numbers by minimizing a novel criterion that includes the coverage probability and normalized average width and show that the proposed models are suitable alternatives to electrical consumption forecasting because they obtain the minimum interval widths that characterize the uncertainty of this type of stochastic process.
Posted Content
Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer
TL;DR: The main goal of this paper is to analyze the general problem of using Convolutional Neural Networks in robots with limited computational capabilities, and to propose general design guidelines for their use.
Proceedings ArticleDOI
Prediction Intervals With LSTM Networks Trained By Joint Supervision
TL;DR: High-quality intervals are obtained with a narrower interval width compared with the classical recurrent neural network approach and could be used to develop robust energy management systems that, for example, consider the worst-case scenario.
Book ChapterDOI
Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots While Playing Soccer
TL;DR: In this paper, two different CNN-based NAO robot detectors that are able to run in real-time while playing soccer are proposed, one based on the XNOR-Net and the other on the SqueezeNet.
Proceedings ArticleDOI
Neural Network Prediction Interval Based on Joint Supervision
TL;DR: A new prediction interval model based on a joint supervision loss function for capturing the uncertainties associated with the modeled phenomenon is described, and shows that the method is able to generate an interval with narrower width than the covariance method, and maintains the coverage probability.