%{search_type} search results

• Quality Management of Deep Learning Systems.- Can Attention Masks Improve Adversarial Robustness?.- Learner-Independent Data Omission Attacks.- Extraction of Complex DNN Models: Real Threat or Boogeyman?.- Principal Component Properties of Adversarial Samples.- FreaAI: Automated extraction of data slices to test machine learning models.- Density estimation in representation space to predict model uncertainty.- Automated detection of drift in deep learning based classifiers using network embedding.- Quality of syntactic implication of RL-based sentence summarization.- Dependable Neural Networks for Safety Critical Tasks.
• (source: Nielsen Book Data)

This book constitutes the revised selected papers of the Third International Workshop on Engineering Dependable and Secure Machine Learning Systems, EDSMLS 2020, held in New York City, NY, USA, in February 2020. The 7 full papers and 3 short papers were thoroughly reviewed and selected from 16 submissions. The volume presents original research on dependability and quality assurance of ML software systems, adversarial attacks on ML software systems, adversarial ML and software engineering, etc. .
(source: Nielsen Book Data)

• 1. Maladies de l'orbite, de l'appareil lacrymal, des paupières, de la conjonctive, de la cornée, de la sclérotique, de l'iris, et de la choroïde, du cristallin, glaucome
• 2. Ophtalmoscopie, maladies du nerf optique, de la rétine, de la choroïde, du corps vitré, anomalies de la réfraction, hypermétropie, myopie, presbytie, astigmatisme, maladies des muscles de l'oeil, strabisme, etc.

• Regular Dynamics: Newton to Poincare
• KAM Theorem
• (source: Nielsen Book Data)

This text examines methods for separating the signal of physical interest from the contamination by chaotic noise, for investigating the phase space of the chaotic noise and its properties, and for modelling the behaviour of the chaotic noise. The author considers the means of controlling chaotic behaviour and using this control to communicate between source and receiver. The emphasis throughout is on the use of the modern mathematical tools for investigating chaotic behaviour to uncover properties of physical systems.
(source: Nielsen Book Data)
A clear and systematic treatment of time series of data, regular and chaotic, found in nonlinear systems. The text leads readers from measurements of one or more variables through the steps of building models of the source as a dynamical system, classifying the source by its dynamical characteristics, and finally predicting and controlling the dynamical system. It examines methods for separating the signal of physical interest from contamination by unwanted noise, and for investigating the phase space of the chaotic signal and its properties. The emphasis throughout is on the use of modern mathematical tools for investigating chaotic behaviour to uncover properties of physical systems, requiring knowledge of dynamical systems at the advanced undergraduate level and some knowledge of Fourier transforms and other signal processing methods.
(source: Nielsen Book Data)