Unsupervised neuron selection for mitigating catastrophic forgetting in neural networks
By Benjamin Goodrich, Itamar Arel. 2014
20 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Christopher Kanan
- Benjamin Goodrich
- Tyler L. Hayes
- Ronald Kemker
- Tomer Lancewicki
- Junmo Kim
- Heechul Jung
- Minju Jung
In Computer Vision and Pattern Recognition
- Christopher Kanan
- Benjamin Goodrich
- Ronald Kemker
- Tyler L. Hayes
- Herbert Jaeger
- Junmo Kim
- Heechul Jung
- Minju Jung
Citations in the corpus
- Measuring Catastrophic Forgetting in Neural Networks (2017, background): “While catastrophic forgetting occurs in unsupervised frameworks (Draelos et al. 2016; Goodrich and Arel 2014; Triki et al. 2017), we focus on supervised classification.”
- Less-forgetting Learning in Deep Neural Networks (2016, neutral): “An unsupervised approach was proposed in [12].”
- Less-forgetful Learning for Domain Expansion in Deep Neural Networks (2017, methodology): “An unsupervised approach was also proposed in (Goodrich and Arel 2014).”
- Mitigating Catastrophic Forgetting in Temporal Difference Learning with Function Approximation (2015, unknown): “The technique proposed here, dubbed " cluster-select " , has recently been introduced as a powerful technique applied to non-stationary classification tasks [6] [7].”
- Sequential Covariance-Matrix Estimation with Application to Mitigating Catastrophic Forgetting (2015, background): “Note that a more in depth discussion of this technique can be found in [20].”
- Using Conceptors to Manage Neural Long-Term Memories for Temporal Patterns (2017, background): “…trained with backpropagation due to the “catastrophic forgetting” problem (appreciation in Douglas and Sejnowski (2008), partial solutions and further references in French (2003); Grossberg (2005); Goodrich and Arel (2014)) and for most associative memories (exception: Jiang et al. (2016)).”
- Neuron Clustering for Mitigating Catastrophic Forgetting in Supervised and Reinforcement Learning (2015, methodology): “The main approach proposed in this dissertation, dubbed ”cluster-select” [49] [50] [51], essentially modifies the standard feedforward network model by proposing an unsupervised learning component.”