Significance Tests for Neural Networks

@article{Horel2019SignificanceTF,
  title={Significance Tests for Neural Networks},
  author={Enguerrand Horel and Kay Giesecke},
  journal={Econometrics: Econometric \& Statistical Methods - General eJournal},
  year={2019}
}
  • Enguerrand Horel, K. Giesecke
  • Published 11 November 2018
  • Computer Science
  • Econometrics: Econometric & Statistical Methods - General eJournal
Neural networks underpin many of the best-performing AI systems. Their success is largely due to their strong approximation properties, superior predictive performance, and scalability. However, a major caveat is explainability: neural networks are often perceived as black boxes that permit little insight into how predictions are being made. We tackle this issue by developing a pivotal test to assess the statistical significance of the feature variables of a neural network. We propose a… 
Sensitivity based Neural Networks Explanations
TLDR
A way to assess the relative input features importance of a neural network based on the sensitivity of the model output with respect to its input is presented and implemented into an open-source Python package that allows its users to easily generate and visualize explanations for their neural networks.
An Interpretable Neural Network for Parameter Inference
TLDR
An application to an asset pricing problem demonstrates how the PENN can be used to explore nonlinear risk dynamics in financial markets, and to compare empirical nonlinear effects to behavior posited by financial theory.
Asset Pricing with Neural Networks: A Variable Significant Test
TLDR
The proposed test permits one to assess the statistical significance of the input variables in an MLP regression model and is applied to identify the most significant predictors in measuring asset risk premiums.
Asset Pricing with Neural Networks: A Variable Significant Test
TLDR
The main results show the superiority of NN relative to the linear regression for forecasting excess returns benchmarking against naive zero forecasts and the most significant predictors are inflation, percent equity issuing, and default return spread.
Consistent Feature Selection for Analytic Deep Neural Networks
TLDR
It is proved that for a wide class of networks, including deep feed-forward neural networks, convolutional neural Networks, and a major sub-class of residual neural network, the Adaptive Group Lasso selection procedure with GroupLasso as the base estimator is selection-consistent.
DeepVix: Explaining Long Short-Term Memory Network With High Dimensional Time Series Data
TLDR
This paper aims to combine the strengths of both data science fields into a unified system, called DeepVix, which focuses on the visual explainability of the multivariate time-series predictions using neural networks.
Fundamental Issues Regarding Uncertainties in Artificial Neural Networks
TLDR
This work provides a discussion of the standard interpretations of this problem and shows how a quantitative approach based upon long standing methods can be practically applied on the task of early diagnosis of dementing diseases using Magnetic resonance Imaging.
Neural Networks and Value at Risk
TLDR
This design feature enables the balanced incentive recurrent neural network (RNN) to outperform the single incentive RNN as well as any other neural network or established approach by statistically and economically significant levels.
Fe b 20 20 Fundamental Issues Regarding Uncertainties in Artificial Neural Networks .
TLDR
This work provides a discussion of the standard interpretations of this problem and shows how a quantitative approach based upon long standing methods can be practically applied on the task of early diagnosis of dementing diseases using Magnetic resonance Imaging.
Computationally Efficient Feature Significance and Importance for Machine Learning Models
TLDR
A simple and computationally efficient significance test for the features of a machine learning model that identifies the statistically significant features as well as feature interactions of any order in a hierarchical manner, and generates a model-free notion of feature importance.
...
1
2
3
...

References

SHOWING 1-10 OF 64 REFERENCES
Learning in Artificial Neural Networks: A Statistical Perspective
  • H. White
  • Computer Science
    Neural Computation
  • 1989
TLDR
Concepts and analytical results from the literatures of mathematical statistics, econometrics, systems identification, and optimization theory relevant to the analysis of learning in artificial neural networks are reviewed.
Neural model identification, variable selection and model adequacy
In recent years an impressive array of publications has appeared claiming considerable successes of neural networks in modelling financial data but sceptical practitioners and statisticians are still
Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings
  • H. White
  • Computer Science
    Neural Networks
  • 1990
Learning Important Features Through Propagating Activation Differences
TLDR
DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of a neural network on a specific input by backpropagating the contributions of all neurons in the network to every feature of the input, is presented.
Some Asymptotic Results for Learning in Single Hidden-Layer Feedforward Network Models
Abstract We investigate the properties of a recursive estimation procedure (the method of “back-propagation”) for a class of nonlinear regression models (single hidden-layer feedforward network
Understanding the difficulty of training deep feedforward neural networks
TLDR
The objective here is to understand better why standard gradient descent from random initialization is doing so poorly with deep neural networks, to better understand these recent relative successes and help design better algorithms in the future.
Nonparametric Inferences for Additive Models
TLDR
The generalized likelihood ratio (GLR) tests are extended to additive models, using the backfitting estimator, and it is proved that the GLR tests are asymptotically optimal in terms of rates of convergence for nonparametric hypothesis testing.
...
1
2
3
4
5
...