Improving the interpretability of deep neural networks with stimulated learning

By Shawn Tan, Khe Chai Sim, Mark John Francis Gales. 2015

47 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

In Signal Processing

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Architecture modification Others: [259] [261] [259]”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “While a single linear transformation may be interpreted by looking at the weights from the input features to each of the output classes, multiple layers with non-linear interactions at every layer imply disentangling a super complicated nested structure which is a difficult task and potentially even”
Deep Learning for Audio Signal Processing (2019, background): “, [16], [151]), or investigate which parts of the input a prediction is based on”
Artificial Intelligence in Surgery: Promises and Perils (2018, background): “54,55 However, many of these efforts remain in their infancy, and surgeon input early in the design of AI algorithms may be helpful improving accountability and interpretability of big data analyses.”
On Multi-Domain Training and Adaptation of End-to-End RNN Acoustic Models for Distant Speech Recognition (2017, background): “There has been some effort on analyzing the hidden features of a clean-trained model in order to understand how the final phoneme-discriminative features are generated by the network [8].”
Stimulated Deep Neural Network for Speech Recognition (2016, methodology): “In order to enhance interpretation, stimulated learning [7] has been proposed to augment the DNN optimization with regularization at the hidden-layer activation level.”
Low-Resource Speech Recognition and Keyword-Spotting (2017, background): “To address this problem stimulated network training has been proposed [29,32,25].”