Rule-Injection Hints as a Means of Improving Network Performance and Learning Time

By S. Suddarth, Y. Kergosien. 1990

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

A Model of Inductive Bias Learning (2000, methodology): “Other similar approaches include Suddarth and Kergosien (1990), Suddarth and Holden (1991), Abu-Mostafa (1993).”
Learning to Navigate in Complex Environments (2016, methodology): “Auxiliary tasks have often been used to facilitate representation learning (Suddarth & Kergosien, 1990).”
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning (2020, background): “Early works sometimes referred to this as including “hints” (Suddarth and Kergosien, 1990; Abu-Mostafa, 1990) to improve learning.”
A survey and critique of multiagent deep reinforcement learning (2018, background): “Suddarth and Kergosien [311] presented a minimal example of a small neural networkwhere itwas shown that adding an auxiliary task effectively removed local minima.”
Multitask Learning (1997, methodology): “(Suddarth & Kergosien 1990; Suddarth & Holden 1991) used extra outputs toinject rule hintsinto networks about what they should learn.”
Learning to Learn (1998, unknown): “MTL learning in this study differed from several other MTL efforts [Abu-Mostafa, 1994; Suddarth, 1990; Suddarth and Holden, 1991; Caruana, 1993] because the differ-”
Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images (2017, unknown): “In [14], it combined an auxiliary unsupervised learning task to help the supervised training of a neural network; the intermediate layers are shared among both the supervised and unsupervised learning tasks.”
Hyperbolic Discounting and Learning over Multiple Horizons (2019, methodology): “Operating over multiple time scales has a long history in RL. Sutton (1995) generalizes the work of Singh (1992) and Dayan and Hinton (1993) to formalize a multi-time scale TD learning model theory.”
Multitask Learning: A Knowledge-Based Source of Inductive Bias (1993, result): “This work is most similar to that on providing hints to networks (Abu-Mostafa 1989)( Suddarth & Kergosien 1990 )(Suddarth & Holden 1991).”
Semi-supervised Learning with Ladder Networks (2015, unknown): “Combining an auxiliary task to help train a neural network was proposed by Suddarth and Kergosien (1990).”