Early experience with low-pass filtered images facilitates visual category learning in a neural network model

<p>Dataset consisting of neural network models trained on low-pass filtered and intact images. </p> <p><br></p> <p>Related to our paper: </p> <p>Jinsi* O, Henderson* MM, Tarr MJ (2023) Early experience with low-pass filtered images facilitates visual category learning in a neural network model. PLoS ONE 18(1): e0280145. <a href="https://doi.org/10.1371/journal.pone.0280145" target="_blank">https://doi.org/10.1371/journal.pone.0280145</a></p> <p><br></p> <p>Each .tar file contains .csv and .pt files resulting from one method of model training (grayscale or colored images, training from-scratch on images from ecoset or fine-tuning models on imagenet). Numbered folders correspond to models initialized with different random seeds. Different files in each folder correspond to different blur conditions. </p> <p>See paper for more details.</p> <p><br></p> <p>For all experiment code, see our github repository at: <a href="https://github.com/tarrlab/startingblurry" target="_blank">https://github.com/tarrlab/startingblurry</a></p> <p><br></p> <p>Contact mmhender@cmu.edu or mt01@andrew.cmu.edu with any questions or concerns.</p>