Autonomous Learning Systems: From Data Streams to Knowledge in Real-time

201 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Generalized Methodology for Data Analysis (2018, methodology): “where μN is the mean of {x}N ; XN is the mean of {xTx}N ; μN and XN can be updated recursively using [18] { μk = k−1 k μk−1 + (1)k xk; μ1 = x1; Xk = k−1 k Xk−1 + (1)k xk xk; X1 = x1 x1; k = 1, 2, .”
Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios (2019, methodology): “The recursive mean μk of the λ , where λ(Ui) is the highest score of confidence Ui obtained, is calculated according to the Equation (12) [26].”
Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference (2020, background): “Moreover, data density can be updated recursively as detailed in [26].”
Novelty Detection and Learning from Extremely Weak Supervision (2019, methodology): “The recursive mean μi of the λ max for the labeled data samples is used to detect sudden drop of the confidence generated by the xClass classifier when a new unknown class arrives and can be calculated as follows [19]:”
Deep rule-based classifier with human-level performance and characteristics (2018, methodology): “In this paper, we offer a principally new approach, which combines the advantages of both, the recently introduced self-organising non-parametric FRB systems [2], [7], , applied to classification problem [3] with the concept of a massively parallel multi-layer structure that deep learning benefits f”