Symbolic-Neural Systems and the Use of Hints for Developing Complex Systems
By S. Suddarth, A. Holden. 1991
Subfields: Model Architectures, Knowledge Graphs & Representation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Model Architectures
- Ronan Collobert
- Yoshua Bengio
- Koray Kavukcuoglu
- Jason Aaron Edward Weston
- Li Deng
- Richard Socher
- L. Eon Bottou
- Christopher D. Manning
In Knowledge Graphs & Representation
- Jason Aaron Edward Weston
- Joseph O'Sullivan
- Sebastian Thrun
- R. Caruana
- Gregory F. Cooper
- Constantin F. Aliferis
- Tom Michael Mitchell
- Jonathan Baxter
Citations in the corpus
- Natural Language Processing (Almost) from Scratch (2011, background): “It is then sufficient to train a model that computes multiple outputs for each pattern (Suddarth and Holden, 1991).”
- A Model of Inductive Bias Learning (2000, methodology): “Other similar approaches include Suddarth and Kergosien (1990), Suddarth and Holden (1991), Abu-Mostafa (1993).”
- Predicting dire outcomes of patients with community acquired pneumonia (2005, background): “See [25–27] for details about MTL and [28] for other ways of using extra outputs to bias learning.”
- 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).”
- Learning to Learn (1998, unknown): “The work described in this paper builds on prior efforts by [Suddarth and Holden, 1991] and [Abu-Mostafa, 1994] (Section 2.”
- Is Learning The n-th Thing Any Easier Than Learning The First? (1995, background): “Learning with hints [1] [4] [6] [16] constructs a neural network with n output units, one for each function f k (k = 1; 2; : : : ; n ).”
- Clustering Learning Tasks and the Selective Cross-Task Transfer of Knowledge (1998, background): “An empirical study carried out in a mobile robot domain shows that TC outperforms its unselective counterpart in situations where only a small number of tasks is relevant.”
- Lifelong Learning: A Case Study. (1995, methodology): “While some authors [52, 44] have proposed to process the support sets and the training set sequentially, others [58, 9, 5] are in favor of training g in parallel, using all n tasks simultaneously.”