Nolan S. Dey
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nolan S. Dey has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Wong
Department of System Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada
1 shared publication - Bryan Tripp
Systems Design Engineering Department, University of Waterloo, Waterloo, ON, Canada
1 shared publication - Graham William Taylor
University of Guelph
1 shared publication - J. Eric Taylor1 shared publication
Latest Publications
- Open Access
Identifying and interpreting tuning dimensions in deep networks
In neuroscience, a tuning dimension is a stimulus attribute that accounts for much of the activation variance of a group of neurons. These are commonly used to decipher the responses of such groups. While researchers have attempted to manually identify an analogue to these tuning dimensions in deep neural networks, we are unaware of an automatic way to discover them. This work contributes an unsupervised framework for identifying and interpreting "tuning dimensions" in deep networks. Our method correctly identifies the tuning dimensions of a synthetic Gabor filter bank and tuning dimensions of the first two layers of InceptionV1 trained on ImageNet.
Open AccessIdentifying and interpreting tuning dimensions in deep networks
In neuroscience, a tuning dimension is a stimulus attribute that accounts for much of the activation variance of a group of neurons. These are commonly used to decipher the responses of such groups. While researchers have attempted to manually identify an analogue to these tuning dimensions in deep neural networks, we are unaware of an automatic way to discover them. This work contributes an unsupervised framework for identifying and interpreting "tuning dimensions" in deep networks. Our method correctly identifies the tuning dimensions of a synthetic Gabor filter bank and tuning dimensions of the first two layers of InceptionV1 trained on ImageNet.