Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability

By J. Urgen Schmidhuber. 1995

How researchers see this paper

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

1. Ricardo Vilalta
2. Youssef Drissi
3. Youssef Drissi
4. Jian Zhao
5. Han-Jia Ye
6. Frank Hutter
7. Wenbin Li
8. J. Urgen Schmidhuber

Citations in the corpus

• Deep learning in neural networks: An overview (2014, background): “A general approach (Schmidhuber, 1995) for both SL and RL seeks to compactly encode weights of large NNs (Schmidhuber, 1997) through programs written in a universal programming language (Gödel, 1931; Church, 1936; Turing, 1936; Post, 1936).”
• Incremental self-improvement for life-time multi-agent reinforcement learning (1996, methodology): “Each animat makes use of an assembler-like programming language similar to the one in (Schmidhuber, 1995b).”
• A Perspective View and Survey of Meta-Learning (2002, background): “The idea of making no fundamental differences between learning and meta-learning is shared by several researchers (Schmidhuber (1995)).”