We present an overview of current research on artificial neural networks, emphasizing a statistical perspective. We view neural networks as parameterized graphs that make probabilistic assumptions about data, and view learning algorithms as methods for finding parameter values that look probable in the light of the data. We discuss basic issues in representation and learning, and treat some of the practical issues that arise in fitting networks to data. We also discuss links between neural networks and the general formalism of graphical models.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7186 |
| Date | 13 March 1996 |
| Creators | Jordan, Michael I., Bishop, Christopher M. |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 26 p., 372415 bytes, 583775 bytes, application/postscript, application/pdf |
| Relation | AIM-1562, CBCL-131 |
Page generated in 0.0023 seconds