Cracking the neural code for word recognition in convolutional neural networks

arXiv:2403.06159v1 Announce Type: new
Abstract: Learning to read places a strong challenge on the visual system. Years of expertise lead to a remarkable capacity to separate highly similar letters and encode their relative positions, thus distinguishing words such as FORM and FROM, invariantly over a large range of sizes and absolute positions. How neural circuits achieve invariant word recognition remains unknown. Here, we address this issue by training deep neural network models to recognize written words and then analyzing how …

abstract arxiv capacity challenge code convolutional neural networks cs.cv encode expertise form networks neural networks q-bio.nc recognition type visual word words