Inductive Bias Transfer

machine learning and neuroscience
inductive bias transfer
Inductive Bias Transfer

The mammalian visual system generalizes robustly across a wide range of perturbations and changes of contexts, while state of the art computer vision networks are easily thrown off. One way to explain this generalization ability are better inductive biases encoded in the representations of visual stimuli throughout the visual cortex. We are studying mechanisms to transfer inductive biases between brains and machines to improve the generalization ability of artificial networks, and get a better understanding of what lets real brains generalize so well.


Publications

Lab members are shown in this color. Preprints are shown in this color.

2022

Arne Nix, Suhas Shrinivasan, Edgar Y. Walker, Fabian H. Sinz Can Functional Transfer Methods Capture Simple Inductive Biases? AISTATS 2022

2021

Shahd Safarani, Arne Nix, Konstantin Willeke, Santiago A. Cadena, Kelli Restivo, George Denfield, Andreas S. Tolias, Fabian H. Sinz Towards robust vision by multi-task learning on monkey visual cortex NeurIPS (accepted)
Shahd Safarani, Arne Nix, Konstantin Willeke, Santiago A. Cadena, Kelli Restivo, George Denfield, Andreas S. Tolias, Fabian H. Sinz Towards robust vision by multi-task learning on monkey visual cortex ICLR 2021 Workshop: How Can Findings About The Brain Improve AI Systems?

2019

Zhe Li, Wieland Brendel, Edgar Walker, Erick Cobos, Taliah Muhammad, Jacob Reimer, Matthias Bethge, Fabian Sinz, Xaq Pitkow, Andreas Tolias Learning from brains how to regularize machines NeurIPS (accepted)
Fabian H. Sinz, Xaq Pitkow, Jacob Reimer, Matthias Bethge, Andreas S. Tolias Engineering a less artificial intelligence Neuron 103(6)

Oct 2018 - Neuronal Intelligence Lab Start

2017

M. Ren, R. Liao, R. Urtasun, F. H. Sinz, R. S. Zemel Normalizing the normalizers: Comparing and extending network normalization schemes ICLR
T. Nguyen, W. Lui, F. Sinz, R. G. Araniuk, A. S. Tolias, X. Pitkow, A. B. Patel Towards a Cortically Inspired Deep Learning Model: Semi-Supervised Learning, Divisive Normalization, and Synaptic Pruning CCN