Write a Technical Report - Artificial Intelligence

Assignment 1 Directions: Type all answers. Keep a copy of your work. Include your name, student number, course number, and code on every page. Follow all other electronic submission guidelines. 1. Build a case-based reasoner for selection of computer science courses to complete an undergraduate major or a MS degree. Use ASU's course sequences and prerequisites when developing cases for this reasoner 2. Create the remaining frame axioms necessary for the four operators pickup, putdown, stack, and unstack described in rules 4 through 7 of Section 8.4. 3. Given the following rules in a back-chaining expert system application: A ˆ ~ (B) → C(.9) C v D → E(.75) F → A(.6) G → D(.8) The system can conclude the following facts (with confidences): F(.9) B(-.8) G(.7) Use the Stanford certainty Factor algebra to determine E and its confidence. 4. Complete the symbolic evaluations that are required to finish Table 9.4. =========================================== Assignment 2 Directions: Type all answers. Keep a copy of your work. Include your name, student number, course number, and code on every page. Follow all other electronic submission guidelines. 1. Consider the behavior of Winston’s concept learning program when learning the concept “step,” where a step consists of a short box and a tall box placed in contact with each other. Create semantic net representations of four examples of steps and four examples of near misses and show the development of the concept. 2. Discuss problems that can arise from using continuous attributes in data, such as monetary cost (dollars and cents), or the height of an entity (a real number). Suggest some method for addressing this problem of continuous data. 3. Use a backpropagation net to recognize the 10 (hand-written) digits. One approach would be to build a 4 X 6 array of points. When a digit is drawn on this grid it will cover some elements, giving them value 1, and miss others, resulting in a value of 0. This 24-element vector would be the input value to your net. You would build your own training vectors. Explain the number of hidden layers and the number of nodes per layer. You may use this program: Bpnn133u. 4. Using the input pattern [1, 1, -1, 1, -1, -1] as the unconditioned stimulus, use the unsupervised Hebbian learning algorithm to recognize this pattern. Note, this is not exactly like the example in the text. 5. Consider the traveling salesperson problem of Section 12.1.1 in the text. Discuss the problem of selecting an appropriate representation for this problem. Design other appropriate genetic operators and fitness measures for this problem.