Clustering-Based Interpretation of Deep ReLU Network

10/13/2021
by   Nicola Picchiotti, et al.
0

Amongst others, the adoption of Rectified Linear Units (ReLUs) is regarded as one of the ingredients of the success of deep learning. ReLU activation has been shown to mitigate the vanishing gradient issue, to encourage sparsity in the learned parameters, and to allow for efficient backpropagation. In this paper, we recognize that the non-linear behavior of the ReLU function gives rise to a natural clustering when the pattern of active neurons is considered. This observation helps to deepen the learning mechanism of the network; in fact, we demonstrate that, within each cluster, the network can be fully represented as an affine map. The consequence is that we are able to recover an explanation, in the form of feature importance, for the predictions done by the network to the instances belonging to the cluster. Therefore, the methodology we propose is able to increase the level of interpretability of a fully connected feedforward ReLU neural network, downstream from the fitting phase of the model, without altering the structure of the network. A simulation study and the empirical application to the Titanic dataset, show the capability of the method to bridge the gap between the algorithm optimization and the human understandability of the black box deep ReLU networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/22/2018

Deep Learning using Rectified Linear Units (ReLU)

We introduce the use of rectified linear units (ReLU) as the classificat...
research
11/08/2020

Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification

The deep neural networks (DNNs) have achieved great success in learning ...
research
06/23/2021

Numerical influence of ReLU'(0) on backpropagation

In theory, the choice of ReLU'(0) in [0, 1] for a neural network has a n...
research
12/24/2021

Parameter identifiability of a deep feedforward ReLU neural network

The possibility for one to recover the parameters-weights and biases-of ...
research
07/17/2015

Learning Robust Deep Face Representation

With the development of convolution neural network, more and more resear...
research
06/16/2019

A General Interpretation of Deep Learning by Affine Transform and Region Dividing without Mutual Interference

This paper mainly deals with the "black-box" problem of deep learning co...
research
02/13/2021

On the convergence of group-sparse autoencoders

Recent approaches in the theoretical analysis of model-based deep learni...

Please sign up or login with your details

Forgot password? Click here to reset