all AI news
B-cos Networks: Alignment is All We Need for Interpretability. (arXiv:2205.10268v1 [cs.CV])
May 23, 2022, 1:12 a.m. | Moritz Böhle, Mario Fritz, Bernt Schiele
cs.CV updates on arXiv.org arxiv.org
We present a new direction for increasing the interpretability of deep neural
networks (DNNs) by promoting weight-input alignment during training. For this,
we propose to replace the linear transforms in DNNs by our B-cos transform. As
we show, a sequence (network) of such transforms induces a single linear
transform that faithfully summarises the full model computations. Moreover, the
B-cos transform introduces alignment pressure on the weights during
optimisation. As a result, those induced linear transforms become highly
interpretable and align …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Technology Consultant Master Data Management (w/m/d)
@ SAP | Walldorf, DE, 69190
Research Engineer, Computer Vision, Google Research
@ Google | Nairobi, Kenya