DeepAI AI Chat
Log In Sign Up

Deep networks for system identification: a Survey

by   Gianluigi Pillonetto, et al.

Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden properties of the observations. System identification learns mathematical descriptions of dynamic systems from input-output data and can thus benefit from the advances of deep neural networks to enrich the possible range of models to choose from. For this reason, we provide a survey of deep learning from a system identification perspective. We cover a wide spectrum of topics to enable researchers to understand the methods, providing rigorous practical and theoretical insights into the benefits and challenges of using them. The main aim of the identified model is to predict new data from previous observations. This can be achieved with different deep learning based modelling techniques and we discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks. Their parameters have to be estimated from past data trying to optimize the prediction performance. For this purpose, we discuss a specific set of first-order optimization tools that is emerged as efficient. The survey then draws connections to the well-studied area of kernel-based methods. They control the data fit by regularization terms that penalize models not in line with prior assumptions. We illustrate how to cast them in deep architectures to obtain deep kernel-based methods. The success of deep learning also resulted in surprising empirical observations, like the counter-intuitive behaviour of models with many parameters. We discuss the role of overparameterized models, including their connection to kernels, as well as implicit regularization mechanisms which affect generalization, specifically the interesting phenomena of benign overfitting ...


page 1

page 2

page 3

page 4


What can linearized neural networks actually say about generalization?

For certain infinitely-wide neural networks, the neural tangent kernel (...

Quantifying Theory in Politics: Identification, Interpretation and the Role of Structural Methods

The best empirical research in political science clearly defines substan...

Deep Learning for Epidemiologists: An Introduction to Neural Networks

Deep learning methods are increasingly being applied to problems in medi...

Deep Neural Networks and Tabular Data: A Survey

Heterogeneous tabular data are the most commonly used form of data and a...

A novel Multiplicative Polynomial Kernel for Volterra series identification

Volterra series are especially useful for nonlinear system identificatio...

Deep learning: a statistical viewpoint

The remarkable practical success of deep learning has revealed some majo...