Software Open Access

JNJER/2021-04-28_transfer_learning: Experimenting with transfer learning for visual categorization

Laurent Perrinet; JNJER

Providing a framework to implement (and experiment with) transfer learning on deep convolutional neuronal network (DCNN). In a nutshell, transfer learning allows to re-use the knowledge learned on a problem, such as categorizing images from a large dataset, and apply it to a different (yet related) problem, performing the categorization on a smaller dataset. It is a powerful method as it allows to implement complex task de novo quite rapidly (in a few hours) without having to retrain the millions of parameters of a DCNN (which takes days of computations). The basic hypothesis is that it suffices to re-train the last classification layer (the head) while keeping the first layers fixed. Here, these networks teach us also some interesting insights into how living systems may perform such categorization tasks.

Files (137.0 MB)
Name Size
137.0 MB Download
All versions This version
Views 4242
Downloads 22
Data volume 273.9 MB273.9 MB
Unique views 3636
Unique downloads 22


Cite as