| Author | Murthy, Ranjit Murthy |
| Call Number | AIT Thesis no. CS-95-03 |
| Subject(s) | Neural networks (Computer science)
|
| Note | A Thesis Report Submitted in the Partial Fulfillment of the requirement for the degree of
Master of Engineering |
| Publisher | Asian Institute of Technology |
| Abstract | There is a world of effort to create large databases for environmental assessment and for
all kinds of decision affecting local and global environments. The International organizations such
as United nations environment program and many national agencies are collecting all kinds of
information going in trillions of units of information. The increasing concerns of environment at
all levels will cause the database to multiply and thus together with advances in communication
will cause greater interconnection of the databases.
Given access to the vast data, it is necessary to discover the knowledge in the corpus.
Since the number of databases are proliferating, their sizes ever enlarging and their
interconnections globalizing, any contribution, even incremental, towards extracting knowledge
would be of great importance.
In this thesis Unsupervised learning is used to discover knowledge form databases.
Specifically self-organizing maps which maps from a higher dimension to a lower one, are used.
The regularity and pattern observed in one dimension gets retained in the other dimension in the
mapping process. The knowledge extracted from the databases are indicated in terms of pattern
formation and formation of rules. A number of pedagogic databases are taken to demonstrate the
methodology in this paradigm for knowledge discovery. |
| Year | 1995 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Sadananda, Ramakoti; |
| Examination Committee(s) | Murai, Shunji;Shrestha, Surendra;Yulu, Qi; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 1995 |