DECISION TREES DO NOT GENERALIZE TO NEW VARIATIONS

DOI10.1111/j.1467-8640.2010.00366.xzbMath1235.68129OpenAlexW2106004777MaRDI QIDQ3224352

Yoshua Bengio, Clarence Simard, Olivier Delalleau

Publication date: 30 March 2012

Published in: Computational Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1111/j.1467-8640.2010.00366.x

zbMATH Keywords

curse of dimensionalitydecision treesparity function

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (2)

Textual outlier detection with an unsupervised method using text similarity and density peak ⋮ PAC-learning gains of Turing machines over circuits and neural networks

Uses Software

• darch

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the power of small-depth threshold circuits
• Complexity lower bounds for approximation algebraic computation trees
• Multilayer feedforward networks are universal approximators
• Universal artificial intelligence. Sequential decisions based on algorithmic probability.
• Support-vector networks
• Learning Deep Architectures for AI
• Nonlocal Estimation of Manifold Structure
• A Fast Learning Algorithm for Deep Belief Nets
• A formal theory of inductive inference. Part II
• Random forests

This page was built for publication: DECISION TREES DO NOT GENERALIZE TO NEW VARIATIONS