Nais-net: Stable deep networks from non-autonomous differential equations
Abstract This paper introduces Non-Autonomous Input-Output Stable Network (NAIS-Net), a
very deep architecture where each stacked processing block is derived from a time-invariant …
very deep architecture where each stacked processing block is derived from a time-invariant …
[图书][B] Deep neural networks in a mathematical framework
AL Caterini, DE Chang - 2018 - Springer
Over the past decade, Deep Neural Networks (DNNs) have become very popular models for
problems involving massive amounts of data. The most successful DNNs tend to be …
problems involving massive amounts of data. The most successful DNNs tend to be …
Learning stable deep dynamics models
JZ Kolter, G Manek - Advances in neural information …, 2019 - proceedings.neurips.cc
Deep networks are commonly used to model dynamical systems, predicting how the state of
a system will evolve over time (either autonomously or in response to control inputs) …
a system will evolve over time (either autonomously or in response to control inputs) …
Combining recurrent, convolutional, and continuous-time models with linear state space layers
Recurrent neural networks (RNNs), temporal convolutions, and neural differential equations
(NDEs) are popular families of deep learning models for time-series data, each with unique …
(NDEs) are popular families of deep learning models for time-series data, each with unique …
Cpt: Efficient deep neural network training via cyclic precision
Low-precision deep neural network (DNN) training has gained tremendous attention as
reducing precision is one of the most effective knobs for boosting DNNs' training time/energy …
reducing precision is one of the most effective knobs for boosting DNNs' training time/energy …
Nimble: Efficiently compiling dynamic neural networks for model inference
Modern deep neural networks increasingly make use of features such as control flow,
dynamic data structures, and dynamic tensor shapes. Existing deep learning systems focus …
dynamic data structures, and dynamic tensor shapes. Existing deep learning systems focus …
Hierarchical deep learning of multiscale differential equation time-steppers
Nonlinear differential equations rarely admit closed-form solutions, thus requiring numerical
time-stepping algorithms to approximate solutions. Further, many systems characterized by …
time-stepping algorithms to approximate solutions. Further, many systems characterized by …
Step size matters in deep learning
Training a neural network with the gradient descent algorithm gives rise to a discrete-time
nonlinear dynamical system. Consequently, behaviors that are typically observed in these …
nonlinear dynamical system. Consequently, behaviors that are typically observed in these …
Identifying nonlinear dynamical systems with multiple time scales and long-range dependencies
D Schmidt, G Koppe, Z Monfared… - arXiv preprint arXiv …, 2019 - arxiv.org
A main theoretical interest in biology and physics is to identify the nonlinear dynamical
system (DS) that generated observed time series. Recurrent Neural Networks (RNNs) are, in …
system (DS) that generated observed time series. Recurrent Neural Networks (RNNs) are, in …
Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
J Smith, S Linderman… - Advances in Neural …, 2021 - proceedings.neurips.cc
Recurrent neural networks (RNNs) are powerful models for processing time-series data, but
it remains challenging to understand how they function. Improving this understanding is of …
it remains challenging to understand how they function. Improving this understanding is of …