Multiresolution Convolutional Autoencoders

Abstract

We propose a multi-resolution convolutional autoencoder (MrCAE) architecture that integrates and leverages three highly successful mathematical architectures: (i) multigrid methods, (ii) convolutional autoencoders and (iii) transfer learning. The method provides an adaptive, hierarchical architecture that capitalizes on a progressive training approach for multiscale spatio-temporal data. This framework allows for inputs across multiple scales: starting from a compact (small number of weights) network architecture and low-resolution data, our network progressively deepens and widens itself in a principled manner to encode new information in the higher resolution data based on its current performance of reconstruction. Basic transfer learning techniques are applied to ensure information learned from previous training steps can be rapidly transferred to the larger network. As a result, the network can dynamically capture different scaled features at different depths of the network. The performance gains of this adaptive multiscale architecture are illustrated through a sequence of numerical experiments on synthetic examples and real-world spatial-temporal data.

20 pages, 11 figures

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Neural Architecture Search with Reinforcement Learning
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Wide Residual Networks
• Deep learning for universal linear embeddings of nonlinear dynamics
• Understanding Deep Convolutional Networks
• A public turbulence database cluster and applications to study Lagrangian evolution of velocity increments in turbulence
• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• Net2Net: Accelerating Learning via Knowledge Transfer
• MgNet: A Unified Framework of Multigrid and Convolutional Neural Network

Cited by in corpus (2)

• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization