On the Transferability of Representations in Neural Networks Between Datasets and Tasks
Preprint
Abstract
Deep networks, composed of multiple layers of hierarchical distributed representations, tend to learn low-level features in initial layers and transition to high-level features towards final layers. Paradigms such as transfer learning, multi-task learning, and continual learning leverage this notion of generic hierarchical distributed representations to share knowledge across datasets and tasks. Herein, we study the layer-wise transferability of representations in deep networks across a few datasets and tasks and note some interesting empirical observations.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Learning Without Forgetting2016
- On the Correlation and Transferability of Features Between Automatic Speech Recognition and Speech Emotion Recognition2016
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition2014
- IEMOCAP: interactive emotional dyadic motion capture databaseLanguage Resources and Evaluation, 2008