Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
The Interpretable Dictionary in Sparse Coding
arXiv.org
24 Nov 2020
Abstract
Artificial neural networks (ANNs), specifically deep learning networks, have
often been labeled as black boxes due to the fact that the internal
representation of the data is not easily interpretable. In our work, we
illustrate that an ANN, trained using sparse coding under specific sparsity
constraints, yields a more interpretable model than the standard deep learning
model. The dictionary learned by sparse coding can be more easily understood
and the activations of these elements creates a selective feature output. We
compare and contrast our sparse coding model with an equivalent feed forward
convolutional autoencoder trained on the same data. Our results show both
qualitative and quantitative benefits in the interpretation of the learned
sparse coding dictionary as well as the internal activation representations.
Metrics
8 Record Views
Details
- Title
- The Interpretable Dictionary in Sparse Coding
- Creators
- Edward Kim - Drexel UniversityConnor Onweller - University of DelawareAndrew O'BrienKathleen McCoy - University of Delaware
- Publication Details
- arXiv.org
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Other Identifier
- 991021884693004721