Scribd
Upload
10 views2 pages

Evaluation Criteria (Rubrics) : Course Code: PGCA1929 Course Name: Artificial Intelligence & Soft Computing Laboratory

The document describes a course on Artificial Intelligence & Soft Computing Laboratory. It outlines the course code, name, program details, credits, semester, theory/practical split. It then lists the course outcomes and mapping to experiments. It provides evaluation criteria. It also lists 24 experiments to be performed along with the mapping of experiments to course outcomes.

Uploaded by

saini.ritu133499
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
10 views2 pages

Evaluation Criteria (Rubrics) : Course Code: PGCA1929 Course Name: Artificial Intelligence & Soft Computing Laboratory

The document describes a course on Artificial Intelligence & Soft Computing Laboratory. It outlines the course code, name, program details, credits, semester, theory/practical split. It then lists the course outcomes and mapping to experiments. It provides evaluation criteria. It also lists 24 experiments to be performed along with the mapping of experiments to course outcomes.

Uploaded by

saini.ritu133499
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Course Code: PGCA1929

Course Name: Artificial Intelligence & Soft Computing Laboratory


Program: MCA L: 0 T: 0 P: 4
Branch: Computer Applications Credits: 4
Semester: 3rd Contact hours: 4 hours per week
Theory/Practical: Practical Percentage of numerical/design problems: -- 90%
Internal max. marks:70 Duration of end semester exam (ESE): 3hrs
External max. marks:30 Elective status: Core
Total marks: 100

Course Outcomes: Students will be able to:


CO# Course outcomes
CO1 Develop the skills to gain a basic understanding of neural network theory and
fuzzylogic theory.
CO2 Apply artificial neural networks and fuzzy logic theory for various problems.
CO3 Determine the use of Genetic algorithm to obtain optimized solutions to
problems.

Evaluation Criteria (Rubrics)


Excellent Good Satisfactory Poor
(4-5 Marks) (2-3 Marks) (1 Marks) (0 Marks)
The program is
exceptionally well The Program is fairly The program is difficult The program is
Quality of
organised, very easy to easy to read and it to read and gives nearly irrelevant to the
program
follow and it gives gives desired output. to the desired output given program
desired output.
Demonstrate deep Adequate knowledge Superficial knowledge of Is unable to answer
knowledge; Answer the of the topic; Answer topic; only able to answer the questions.
Viva-Voce questions with the questions, but fails basic questions.
explanations and to elaborate.
elaboration.

Artificial Intelligence & Soft Computing Laboratory


PGCA1929
Mapping of syllabus with Course Outcomes and Rubrics
Quality of
CO’s Viva-Voce
Sno. List of Experiments Program Signature
Mapping (5)
(5)
1. Introduction to Matlab and Perform Basic
Commands of Matlab
2. WAP in Matlab to create a matrix and sort it in
Ascending and Descending order
3. WAP in Matlab to perform operations on Matrices
4. WAP in Matlab to check for prime numbers CO2
5. WAP in Python to check for prime numbers CO2
6. Implement Union, Intersection, Complement and CO1
Difference operations on fuzzy sets. Also create
fuzzy relation by Cartesian product of any two
fuzzy sets and perform maxmin composition on
any two fuzzy relations.
7.
8. Use logic programming in Python parse a family CO2
tree and infer the relationships between the family
members.
9. Python script for building a puzzle solver. CO2
10. Implementation of uninformed search techniques in CO2
Python.
Implementation of heuristic search techniques in CO2
11. Python.
12. Python script for tokenizing text data. CO2
13. Extracting the frequency of terms using a Bag of CO2
Words model.
14. Predict the category to which a given piece of text CO2
belongs.
15. Python code for visualizing audio speech signal CO2
16. Python code for Generating audio signals CO2
17. Create a perceptron with appropriate no. of inputs CO1
and outputs. Train it using fixed increment learning
algorithm until no change in weights is required.
Output the final weights.
Implement AND function using ADALINE with CO1
18. bipolar inputs and outputs.
19. Implement AND function using MADALINE with CO1
bipolar inputs and outputs.
20 Construct and test auto associative network for input CO1
vector using HEBB rule.
21 Construct and test auto associative network for Input CO1
vector using outer product rule.
22 Construct and test heteroassociative network for CO1
binary inputs and targets.
23 Create a back propagation network for a given input CO1
pattern. Perform 3 epochs of operation.
24 Maximize the function f(x)=x2 using GA, where x CO3
ranges form 0-25. Perform 6 iterations.

You might also like