Combining Symbolic and Neural Learning

By Jude W. Shavlik. 1994

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

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

In Natural Language Processing

1. Swarat Chaudhuri
2. Rishabh Singh
3. Kevin Ellis
4. Oleksandr Polozov
5. Armando Solar-Lezama
6. Yisong Yue
7. Gary F. Marcus
8. J. Urgen Schmidhuber

In Representation & Self-Supervised Learning

1. Armando Solar-Lezama
2. J. Urgen Schmidhuber
3. Kevin Ellis
4. Yisong Yue
5. Gary F. Marcus
6. Swarat Chaudhuri
7. Rishabh Singh
8. Sjoerd van Steenkiste

Citations in the corpus

• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020, methodology): “Computer scientists such as Ron Sun (Sun, 1996) advocated for hybrid models throughout the 1990s; Shavlik (Shavlik, 1994) showed that it was possible to translate a (limited) subset of logic into neural networks.”
• Deep learning in neural networks: An overview (2014, methodology): “A hybrid approach (Shavlik & Towell, 1989; Towell & Shavlik, 1994) initializes a potentially deep FNN through adomain theory in propositional logic, which may be acquired through explanationbased learning (DeJong & Mooney, 1986; Minton et al., 1989; Mitchell, Keller, & Kedar-Cabelli, 1986).”
• Neurosymbolic Programming (2021, background): “Unifying these two strands of work, Shavlik, 1994 proposed a general learning framework in which an initial neural network, constructed using symbolic knowledge, is refined using data, and new symbolic knowledge is extracted from this refined network.”