Inductive transfer with context-sensitive neural networks

58 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Survey on Multi-Task Learning (2017, neutral): “[9] propose a context-sensitive multi-task”
Machine Lifelong Learning: Challenges and Benefits for Artificial General Intelligence (2011, background): “Since 1995, Silver et al. have proposed several variants of sequential learning and consolidation systems using standard back-propagation neural networks [9, 10 ].”
Fast Context Adaptation via Meta-Learning (2018, methodology): “Silver et al. (2008) proposed context features as a component of inductive transfer, using a predefined one-hot encoded task-specifying context as input to the network.”
Transfer learning using computational intelligence: A survey (2015, methodology): “To verify the effectiveness of csMTL, a set of experiments was designed to detect csMTL and MTL neural networks in their ability to transfer knowledge [59].”
Metalearning: a survey of trends and technologies (2013, background): “Bagging however does not satisfy point 2 of Definition 1, as consecutive random samples from the original dataset are independent from each other, so there is no experience from previous learning episodes involved.”
Lifelong Machine Learning Systems: Beyond Learning Algorithms (2013, background): “Since 1995, Silver et al. have proposed variants of sequential learning and consolidation systems using standard back-propagation neural networks (Silver and Poirier 2004; Silver, Poirier, and Currie 2008).”