scholarly journals Fast-Rate Loss Bounds via Conditional Information Measures with Applications to Neural Networks

2021 ◽  
Author(s):  
Fredrik Hellstrom ◽  
Giuseppe Durisi
Keyword(s):  
Neural Networks ◽  
Fast Rate ◽  
Information Measures ◽  
Conditional Information ◽  
Rate Loss

Stator fault analysis of three-phase induction motors using information measures and artificial neural networks

2017 ◽  
Vol 143 ◽  
pp. 347-356 ◽  
Author(s):  
Gustavo Henrique Bazan ◽  
Paulo Rogério Scalassara ◽  
Wagner Endo ◽  
Alessandro Goedtel ◽  
Wagner Fontes Godoy ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Induction Motors ◽  
Fault Analysis ◽  
Information Measures ◽  
Three Phase ◽  
Artificial Neural ◽  
Stator Fault

scholarly journals The Information Loss of a Stochastic Map

Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 1021
Author(s):  
James Fullwood ◽  
Arthur J. Parzygnat
Keyword(s):  
Conditional Entropy ◽  
Information Loss ◽  
Shannon Information ◽  
Bayes Rule ◽  
Information Theoretic ◽  
Information Measures ◽  
Related Information ◽  
Conditional Information ◽  
Stochastic Map

We provide a stochastic extension of the Baez–Fritz–Leinster characterization of the Shannon information loss associated with a measure-preserving function. This recovers the conditional entropy and a closely related information-theoretic measure that we call conditional information loss. Although not functorial, these information measures are semi-functorial, a concept we introduce that is definable in any Markov category. We also introduce the notion of an entropic Bayes’ rule for information measures, and we provide a characterization of conditional entropy in terms of this rule.

scholarly journals Synaptic Plasticity in Neural Networks Needs Homeostasis with a Fast Rate Detector

2013 ◽  
Vol 9 (11) ◽  
pp. e1003330 ◽  
Author(s):  
Friedemann Zenke ◽  
Guillaume Hennequin ◽  
Wulfram Gerstner
Keyword(s):  
Neural Networks ◽  
Synaptic Plasticity ◽  
Fast Rate

scholarly journals Early detection of cryostorage tank failure using a weight-based monitoring system

2018 ◽  
Author(s):  
Zahava P. Michaelson ◽  
Sai T. Bondalapati ◽  
Selma Amrane ◽  
Robert W. Prosser ◽  
Daniel M. Hill ◽  
...  
Keyword(s):  
New York ◽  
Weight Loss ◽  
Monitoring System ◽  
Fast Rate ◽  
Operating Conditions ◽  
Alarm System ◽  
Tank Wall ◽  
Safety Mechanism ◽  
Constant Rate ◽  
Rate Loss

AbstractObjectTo study the ability of custom-built, web-enabled scales to monitor liquid nitrogen (LN2) levels in cryostorage dewars.DesignLaboratory studySettingA large academic fertility center in New York City.InterventionsCryostorage dewars were placed on top of the custom-engineered scales with continuous real-time monitoring, and weight and temperature data were recorded in the setting of slow, medium, and fast rate-loss of LN2 designed to mimic models of tank failures.Main Outcome MeasuresWeights were continuously monitored and recorded, with a calculated alarm trigger set at 10% weight loss. Temperature within the tanks was simultaneously monitored with probes placed near the top of the tanks, with calculated alarms using a −185 °C as the threshold. For the “slow rate-loss” simulations, tanks were left intact and closed in usual operating conditions, and LN2 was allowed to evaporate at the normal rate. For the “medium rate-loss” simulation, the foam core of the tank neck was removed and the insulating vacuum was eliminated by making a 1/16 inch hole in the outer tank wall. For the “fast rate-loss” simulation, a 1/16” hole was made through the outer tank wall and LN2 was released at a rate of 0.15 L/second. All simulations were performed in duplicate.ResultsWith an intact and normally functioning tank, a 10% loss in LN2 occurred in 4.2-4.9 days. Warming to −185 °C occurred in 37.8 - 43.7 days, over 30 days after the weight-based alarm was triggered. Full evaporation of LN2required 36.8 days. For the medium rate-loss simulation, a 10% loss in LN2 occurred in 0.8 h. Warming to −185 °C occurred in 3.7 - 4.8 hours, approximately 3 hours after the weight-based alarm was triggered. For the fast rate-loss simulation, a 10% weight loss occurred within 15 seconds and tanks were completely depleted in under 3 minutes. Tank temperatures began to rise immediately and at a relatively constant rate of 43.9 °C/hour and 51.6 °C/hour. Temperature alarms would have sounded within 0.37 and 0.06 hours after the breech.ConclusionsThis study demonstrates that a weight-based, automated alarm system can detect tank failures prior to a temperature-based alarm system, in some cases over a month in advance. In combination with existing safety mechanisms such as temperature probes, a weight-based monitoring system could serve as a redundant safety mechanism for added protection of cryopreserved reproductive tissues.

scholarly journals Generalizations of Fano’s Inequality for Conditional Information Measures via Majorization Theory

Entropy ◽  
2020 ◽  
Vol 22 (3) ◽  
pp. 288
Author(s):  
Yuta Sakai
Keyword(s):  
Asymptotic Behavior ◽  
Marginal Distribution ◽  
Broad Class ◽  
Acta Math ◽  
Infinite Dimensional ◽  
Information Measures ◽  
Asymptotic Equipartition Property ◽  
Dimensional Version ◽  
Conditional Information ◽  
Error Probabilities

Fano’s inequality is one of the most elementary, ubiquitous, and important tools in information theory. Using majorization theory, Fano’s inequality is generalized to a broad class of information measures, which contains those of Shannon and Rényi. When specialized to these measures, it recovers and generalizes the classical inequalities. Key to the derivation is the construction of an appropriate conditional distribution inducing a desired marginal distribution on a countably infinite alphabet. The construction is based on the infinite-dimensional version of Birkhoff’s theorem proven by Révész [Acta Math. Hungar. 1962, 3, 188–198], and the constraint of maintaining a desired marginal distribution is similar to coupling in probability theory. Using our Fano-type inequalities for Shannon’s and Rényi’s information measures, we also investigate the asymptotic behavior of the sequence of Shannon’s and Rényi’s equivocations when the error probabilities vanish. This asymptotic behavior provides a novel characterization of the asymptotic equipartition property (AEP) via Fano’s inequality.

The one-level functional equation of multi-rate loss systems

2003 ◽  
Vol 14 (2) ◽  
pp. 107-118 ◽  
Author(s):  
Harro L. Hartmann ◽  
Martin Knoke
Keyword(s):  
Functional Equation ◽  
Loss Systems ◽  
The One ◽  
Rate Loss
Sign in / Sign up

Export Citation Format

Share Document