Explaining Deep Learning Representations by Tracing the Training Process

09/13/2021
by   Lukas Pfahler, et al.
58

We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process. This way we can a) find the most influential training examples during training and b) analyze which classes attributed most to the final representation. Our method is general: it can be wrapped around any iterative optimization procedure and covers a variety of neural network architectures, including feed-forward networks and convolutional neural networks. We first propose a method for stochastic training with single training instances, but continue to also derive a variant for the common mini-batch training. In experimental evaluations, we show that our method identifies highly representative training instances that can be used as an explanation. Additionally, we propose a visualization that provides explanations in the form of aggregated statistics over the whole training process.

READ FULL TEXT

page 5

page 6

page 7

research
06/23/2016

DropNeuron: Simplifying the Structure of Deep Neural Networks

Deep learning using multi-layer neural networks (NNs) architecture manif...
research
03/10/2021

Reframing Neural Networks: Deep Structure in Overcomplete Representations

In comparison to classical shallow representation learning techniques, d...
research
03/01/2019

Aggregating explainability methods for neural networks stabilizes explanations

Despite a growing literature on explaining neural networks, no consensus...
research
10/16/2018

Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks

In this paper, we introduce a novel methodology for characterising the p...
research
11/19/2015

Adjustable Bounded Rectifiers: Towards Deep Binary Representations

Binary representation is desirable for its memory efficiency, computatio...
research
09/25/2019

Explaining and Interpreting LSTMs

While neural networks have acted as a strong unifying force in the desig...
research
03/20/2019

Representative Datasets: The Perceptron Case

One of the main drawbacks of the practical use of neural networks is the...

Please sign up or login with your details

Forgot password? Click here to reset