M.S./ PH.D PROGRAM IN CONSCIOUSNESS STUDIES
A collaborative Program of the Bhaktivedanta Institute and
Birla Institute of Technology & Science, Pilani
CONS
ZG551: ARTIFICIAL INTELLIGENCE AND CONSCIOUSNESS
General Information
Course Descriptions
The field of Artificial Intelligence has a natural connection with consciousness. The field is a broad topic, consisting of different sub-fields, from machine vision, natural language understanding, problem solving to expert systems. The element that these sub-fields of AI have in common is the creation of machines that can "think". The theory and insights brought about by AI research will not only set the trend in the future of computing, but also bear significantly upon the field of consciousness studies. This course would primarily focus on computable and non-computable models of cognitive tasks. The first part of the course would focus on symbolic and connectionist computational models. The challenges that an AI researcher faces while processing natural language would be investigated in the second part of the course. The third part of the course would ask the students to critique some selected papers that either demonstrate how understanding of human consciousness via cognitive models could contribute to the development of AI methodologies, or raise the philosophical issues underlying claims of machines as autonomous/thinking agents.
Grading
Materials:
The course handouts (Vol. 1 and Vol. 2) provided to all registered students
contains all the relevant materials. Students may be provided further handouts
if necessary. Students are advised to refer to many relevant books on this
topic available in the library.
Number of Class-room
Hours: 43
Modules
Part I (Computational
Models)
|
Lectures |
Course Outline |
Lectures |
|
#1- 3 |
Computer Organization: Logic Gates and Flip-flops, Binary Adders, Encoder and Decoder |
Three |
|
#4-9 |
Computation, Effective Procedure, Turing Machine, Universal Turing Machine and Halting Problem |
Six |
|
#10-15 |
Connectionist Computational model: Simple Perceptron, Back-propagation Networks, Hopfield Network and Kohonen Network |
Six |
|
|
Quantum Computation (optional) |
Optional |
Part II (Natural
Language Understanding)
|
Lectures |
Course Outline |
No. of Lectures |
|
#16 |
Automatic Text Analysis and Classification |
1 |
|
#17 |
File Structures |
1 |
|
#18 |
Search Strategies |
1 |
|
#19 |
Probabilistic Retrieval |
1 |
|
#20 |
Evaluation |
1 |
|
#21 |
Finite-State-Transducers for text extraction, Basic NLP Parsing Algorithms |
1 |
|
#22 |
Advanced Parsing Methods, Disambiguation, and Robust/Partial Parsing |
1 |
|
#23 |
Discourse-Level Processing: Ellipsis, Anaphora, etc. |
1 |
|
#24 |
Knowledge-Based and Example-Based Machine Translation |
1 |
|
#25 |
Natural Language Generation Methods |
1 |
|
#26 |
Statistical Machine Translation |
1 |
·
Discussion of Research Papers on NLP
|
Lectures |
Paper |
No. of Lectures |
|
#27 |
An overview of empirical natural language processing, AI Magazine Vol. 18, No. 4, Winter 1997 |
1 |
|
#28 |
Statistical Techniques for Natural Language Parsing, AI Magazine, Vol.18, No. 4, Winter 1997 |
1 |
|
#29 |
Corpus-based Approaches to Semantic Interpretation in NLP, AI Magazine, Vol. 18, No. 4, Winter 1997 |
1 |
|
#30 |
Automated Knowledge Acquisition for Machine Translation, AI Magazine, Vol.18, No. 4, Winter 1997 |
1 |
|
#31 |
Empirical Methods in Information Extraction, AI Magazine, Vol.18, No. 4, Winter 1997 |
1 |
Part III (Critique of Research Papers)
Minds, Brains and Programs, John R. Searle, The Philosophy of Artificial Intelligence, M. A. Boden (Ed.)