Deep Autoencoders
University of TorontoImage representation
The Deep Autoencoders model is a frontier image representation model from University of Toronto with 139808256.0 parameters.
About Deep Autoencoders
We show how to learn many layers of features on color images and we use these features to initialize deep autoencoders. We then use the autoencoders to map images to short binary codes. Using semantic hashing [6], 28-bit codes can be used to retrieve
Details
- Provider
- University of Toronto
- Task
- Image representation
- Parameters
- 139808256.0
- Released
- 2011-04-29