Cappell B, Stoll A, Umah WC, Egger B (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: ML Research Press
Book Volume: 243
Pages Range: 1-10
Conference Proceedings Title: Proceedings of Machine Learning Research
Event location: New Orleans, LA, USA
Computational models trained on a large amount of natural images are the state-of-the-art to study human vision – usually adult vision. Computational models of infant vision and its further development are gaining more and more attention in the community. In this work we aim at the very beginning of our visual experience – pre- and post-natal retinal waves which suggest to be a pre-training mechanism for the primate visual system at a very early stage of development. We see this approach as an instance of biologically plausible data driven inductive bias through pre-training. We built a computational model that mimics this development mechanism by pre-training different artificial convolutional neural networks with simulated retinal wave images. The resulting features of this biologically plausible pre-training closely match the V1 features of the primate visual system. We show that the performance gain by pre-training with retinal waves is similar to a state-of-the art pre-training pipeline. Our framework contains the retinal wave generator, as well as a training strategy, which can be a first step in a curriculum learning based training diet for various models of development. We release code, data and trained networks to build the basis for future work on visual development and based on a curriculum learning approach including prenatal development to support studies of innate vs. learned properties of the primate visual system. An additional benefit of our pre-trained networks for neuroscience or computer vision applications is the absence of biases inherited from datasets like ImageNet.
APA:
Cappell, B., Stoll, A., Umah, W.C., & Egger, B. (2023). ReWaRD: Retinal Waves for Pre-Training Artificial Neural Networks Mimicking Real Prenatal Development. In Marco Fumero, Emanuele Rodola, Clementine C. J. Domine, Francesco Locatello, Gintare Karolina Dziugaite, Mathilde Caron (Eds.), Proceedings of Machine Learning Research (pp. 1-10). New Orleans, LA, USA: ML Research Press.
MLA:
Cappell, Benjamin, et al. "ReWaRD: Retinal Waves for Pre-Training Artificial Neural Networks Mimicking Real Prenatal Development." Proceedings of the 1st Workshop on Unifying Representations in Neural Models, UniReps 2023, New Orleans, LA, USA Ed. Marco Fumero, Emanuele Rodola, Clementine C. J. Domine, Francesco Locatello, Gintare Karolina Dziugaite, Mathilde Caron, ML Research Press, 2023. 1-10.
BibTeX: Download