Transfer Learning

Inter-and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition
Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields …
Nishai Kooverjee, Steven James, Terence Van Zyl
PDF Cite
Composing Value Functions in Reinforcement Learning
A talk on combining previously learned value functions to solve new tasks without further training.
1 Jun 2019 Long Beach Convention Center
Learning to Plan with Portable Symbols
We present a framework for autonomously learning a portable symbolic representation that describes a collection of low-level continuous …
Steven James, Benjamin Rosman, George Konidaris
PDF Cite