The Parallel Transfer of Task Knowledge Using Dynamic Learning Rates Based on a Measure of Relatedness

By Daniel L. Silver. 1996

How researchers see this paper

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

Citations in the corpus

Lifelong Generative Modeling (2017, methodology): “This supervised approach was later improved through the use of dynamic learning rates [115], core-sets [114] and multi-head classifiers [31].”
A Model of Inductive Bias Learning (2000, background): “In this context, see Silver and Mercer (1996), Thrun and O’Sullivan (1996).”
Inductive transfer with context-sensitive neural networks (2008, methodology): “Multiple task learning (MTL) neural networks are one of the better documented methods of inductive transfer of task knowledge (Caruana 1997; Silver and Mercer 1996).”
Life-long learning based on dynamic combination model (2017, background): “Page 6 of 24 Ac ce pt ed M an us cr ip t in [18], to transfer the representation of a known task to a new one.”
Deep learning of the tissue-regulated splicing code (2014, background): “We chose an interval that more finely differentiates tissue-specific AS for this task, where a difference of 40.15 would be labeled as a change in PSI levels.”
Neural networks with a self-refreshing memory: Knowledge transfer in sequential learning tasks without catastrophic forgetting (2000, background): “The former, referred to as ‘functional’ transfer (Silver and Mercer 1996), is based on concurrent learning.”
Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions (2002, background): “In a related work, Silver and Mercer (1996) have developed a system consisting of task networks and an experience network.”
Lifelong Machine Learning Systems: Beyond Learning Algorithms (2013, methodology): “The simplest method of retaining task knowledge is in functional form such as the training examples (Silver and Mercer 1996).”
Knowledge Transfer in Deep convolutional Neural Nets (2007, background): “Although these two techniques both rely upon the creation of an internal representation of raw data to enhance a net’s ability to learn multiple tasks, they represent two fundamentally different methods of knowledge transfer — representational and functional.(7) In representational transfer, which P”
Machine Lifelong Learning: Challenges and Benefits for Artificial General Intelligence (2011, background): “Experimental results indicate that effective learning excels under functional transfer whereas efficient learning requires representation transfer [7].”