Identifying Interpretable Visual Features in Artificial and Biological
Neural Systems

v1v2 (latest)

Identifying Interpretable Visual Features in Artificial and Biological Neural Systems

17 October 2023

David A. Klindt

Francisco Acosta

Frédéric Poitevin

ArXiv (abs)PDF HTML

Papers citing "Identifying Interpretable Visual Features in Artificial and Biological Neural Systems"

13 / 13 papers shown

Title
Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Charles OÑeill David Klindt David Klindt 171 2 0 20 Nov 2024
Towards Automated Circuit Discovery for Mechanistic Interpretability Arthur Conmy Augustine N. Mavor-Parker Aengus Lynch Stefan Heimersheim Adrià Garriga-Alonso 66 319 0 28 Apr 2023
Toy Models of Superposition Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer T. Henighan ... Sam McCandlish Jared Kaplan Dario Amodei Martin Wattenberg C. Olah AAML MILM 198 380 0 21 Sep 2022
How Well do Feature Visualizations Support Causal Understanding of CNN Activations? Roland S. Zimmermann Judy Borowski Robert Geirhos Matthias Bethge Thomas S. A. Wallis Wieland Brendel FAtt 63 33 0 23 Jun 2021
Towards falsifiable interpretability research Matthew L. Leavitt Ari S. Morcos AAML AI4CE 80 68 0 22 Oct 2020
Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs Jonathan Frankle D. Schwab Ari S. Morcos 96 143 0 29 Feb 2020
Understanding Neural Networks via Feature Visualization: A survey Anh Nguyen J. Yosinski Jeff Clune FAtt 76 162 0 18 Apr 2019
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations Francesco Locatello Stefan Bauer Mario Lucic Gunnar Rätsch Sylvain Gelly Bernhard Schölkopf Olivier Bachem OOD 143 1,473 0 29 Nov 2018
On the importance of single directions for generalization Ari S. Morcos David Barrett Neil C. Rabinowitz M. Botvinick 85 333 0 19 Mar 2018
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric Richard Y. Zhang Phillip Isola Alexei A. Efros Eli Shechtman Oliver Wang EGVM 384 11,938 0 11 Jan 2018
Neural system identification for large populations separating "what" and "where" David A. Klindt Alexander S. Ecker Thomas Euler Matthias Bethge 60 122 0 07 Nov 2017
Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review T. Poggio H. Mhaskar Lorenzo Rosasco Brando Miranda Q. Liao 149 576 0 02 Nov 2016
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps Karen Simonyan Andrea Vedaldi Andrew Zisserman FAtt 317 7,321 0 20 Dec 2013