𝔖 Bobbio Scriptorium
✦   LIBER   ✦

On universal learning algorithms

✍ Scribed by Oded Goldreich; Dana Ron

Publisher
Elsevier Science
Year
1997
Tongue
English
Weight
524 KB
Volume
63
Category
Article
ISSN
0020-0190

No coin nor oath required. For personal study only.

✦ Synopsis

We observe that there exists a universal learning algorithm that PAc-learns every concept class within complexity that is linearly related to the complexity of the best learning algorithm for this class. This observation is derived by an adaptation, to the learning context, of Levin's proof of the existence of optimal algorithms for NP.

πŸ“œ SIMILAR VOLUMES

Adaptive and Self-Confident On-Line Lear
Adaptive and Self-Confident On-Line Learning Algorithms
✍ Peter Auer; NicolΓ² Cesa-Bianchi; Claudio Gentile πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 216 KB

We study on-line learning in the linear regression framework. Most of the performance bounds for on-line algorithms in this framework assume a constant learning rate. To achieve these bounds the learning rate must be optimized based on a posteriori information. This information depends on the whole

Encoded pattern classification using con
Encoded pattern classification using constructive learning algorithms based on learning vector quantization
✍ C.N.S. Ganesh Murthy; Y.V. Venkatesh πŸ“‚ Article πŸ“… 1998 πŸ› Elsevier Science 🌐 English βš– 293 KB

A novel encoding technique is proposed for the recognition of patterns using four different techniques for training artificial neural networks (ANNs) of the Kohonen type. Each template or model pattern is overlaid on a radial grid of appropriate size, and converted to a two-dimensional feature array