Improving the interpretability of deep neural networks with stimulated learning
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Deep Neural Networks (DNNs) have demonstrated improvements in acoustic modelling for automatic speech recognition. However, they are often used as a black box, and not much is understood about what each of the hidden layers does. We seek to understand how the activations in the hidden layers change with different input, and how we can leverage such knowledge to modify the behaviour of the model. To this end, we propose stimulated deep learning where stimuli are introduced during the DNN training process to influence the behaviour of the hidden units. Specifically, constraints are applied so that the hidden units of each layer will exhibit phone-dependent regional activities when arranged in a 2-dimensional grid. We demonstrate that such constraints are able to yield visible activation regions without compromising the classification of the network and suppressing the activations for a region affects the classification accuracy of the corresponding phone more than the others.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Understanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Swietojanski, P., & Renals, S. (2014) · 2014 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2014.7078569 · Cited by 218
Research works printed but not linked: 11
- van der maaten, 2008, Visualizing data using t-sne, Journal of Machine Learning Research, 9, 85
- rahman mohamed, 2012, Understanding how deep belief networks perform acoustic modelling, Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing
- povey, 2011, The kaldi speech recognition toolkit, Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, 1
- bergstra, 2010, Theano: A cpu and gpu math compiler in python, Proc 9th Python in Science Conf, 1
- 10.1109/CVPR.2009.5206545 · DOI · Paper page
- david garson, 1991, Interpreting neural-network connection weights, AI Expert, 6, 46
- 10.1109/ICASSP.2014.6853591 · DOI · Paper page
- 10.1016/0954-1810(94)00011-S · DOI · Paper page
- 10.1109/ASRU.2011.6163899 · DOI · Paper page
- 10.1109/MSP.2012.2205597 · DOI · Paper page
- 10.1007/978-3-319-10590-1_53 · DOI · Paper page
Cited by
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
“Architecture modification Others: [259] [261] [259]”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
“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 a questionable one…”
BackgroundArtificial intelligence in surgery: promises and perils
Hashimoto, D. A., Rosman, G., Rus, D., & Meireles, O. R. (2018) · Annals of Surgery · doi:10.1097/sla.0000000000002693 · Cited by 1,468
“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.”
BackgroundDeep Learning for Audio Signal Processing
Purwins, H., Li, B., Virtanen, T., Schluter, J., Chang, S.-Y., & Sainath, T. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2908700 · Cited by 855
Metadata
- Authors
- Tan, S., Sim, K. C., & Gales, M.
- Venue
- 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)
- Publisher
- IEEE
- Published
- 2015-12
- Pages
- 617-623
- OpenAlex
- W2288977568
- Cited by
- 40
- References
- 4
- FWCI
- 3.60
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Improving the interpretability of deep neural networks with stimulated learning. https://app.cochat.ai/papers/10.1109/asru.2015.7404853
- The paper
- Tan, S., Sim, K. C., & Gales, M. (2015). Improving the interpretability of deep neural networks with stimulated learning. 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). https://doi.org/10.1109/asru.2015.7404853
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.