{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/explaining-neural-networks-by-decoding-layer","title":"Explaining Neural Networks by Decoding Layer Activations","arxiv_id":"2005.13630","date":"2020-05-27","proceeding":null,"authors":["Johannes Schneider","Michalis Vlachos"],"abstract":"We present a `CLAssifier-DECoder' architecture (\\emph{ClaDec}) which facilitates the comprehension of the output of an arbitrary layer in a neural network (NN). It uses a decoder to transform the non-interpretable representation of the given layer to a representation that is more similar to the domain a human is familiar with. In an image recognition problem, one can recognize what information is represented by a layer by contrasting reconstructed images of \\emph{ClaDec} with those of a conventional auto-encoder(AE) serving as reference. We also extend \\emph{ClaDec} to allow the trade-off between human interpretability and fidelity. We evaluate our approach for image classification using Convolutional NNs. We show that reconstructed visualizations using encodings from a classifier capture more relevant information for classification than conventional AEs. Relevant code is available at \\url{https://github.com/JohnTailor/ClaDec}","url_abs":"https://arxiv.org/abs/2005.13630v3","url_pdf":"https://arxiv.org/pdf/2005.13630v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"explaining-neural-networks-by-decoding-layer","repo_url":"https://github.com/JohnTailor/ClaDec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.13630","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}