Transfer Learning with Sparse Associative Memories
Machine Learning
2019-09-20 v3 Computer Vision and Pattern Recognition
Machine Learning
Abstract
In this paper, we introduce a novel layer designed to be used as the output of pre-trained neural networks in the context of classification. Based on Associative Memories, this layer can help design Deep Neural Networks which support incremental learning and that can be (partially) trained in real time on embedded devices. Experiments on the ImageNet dataset and other different domain specific datasets show that it is possible to design more flexible and faster-to-train Neural Networks at the cost of a slight decrease in accuracy.
Cite
@article{arxiv.1904.02420,
title = {Transfer Learning with Sparse Associative Memories},
author = {Quentin Jodelet and Vincent Gripon and Masafumi Hagiwara},
journal= {arXiv preprint arXiv:1904.02420},
year = {2019}
}
Comments
Presented at the 28th International Conference on Artificial Neural Networks (ICANN 2019)