Convergence rates 1 Extraction 1 Feature extraction 1 Feature extraction algorithms 1 Feature words 1 Features extraction 1 Formal adaptation 1 Global conver-gence 1 Gradient methods 1 Gradient's methods 1 Gradient-descent 1 Gram matrices 1 History 1 History of engineering and technology 1 Literary works 1 Multilayer neural networks 1 Nesterov accelerated gradient method 1 Nesterov's accelerated gradient method 1 Network layers 1 Neural networks 1 Neural tangent kernel 1 Neural-networks 1 Non-asymptotic 1 Non-asymptotic global convergence 1 Number theory 1 Over-parameterization 1 Overparameterization 1 Parameterization 1 Production process 1 Related factors 1