hw5 - item <P20, F, 1.65> using K-Nearest Neighbor...

This preview shows pages 1–2. Sign up to view the full content.

Q1) In the following neural network, the input has a value of 5 and its range is between 1 to 10, calculate the output x. Note that the transfer function for the nodes in the hidden layer is Hyperbolic Tangent, and for the output node is a Logistic function. Q2) Consider the following point-of-sales transactions (a) Generate the co-occurrence matrix for this transaction. (b) Generate 2 association rules. (c) Measure “support”, “confidence”, and “lift” for the rules you generated in part (b). Can you specify a useful (strong) rule? Q3) Consider the training data set shown in the following Table. We want to classify the new

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: item <P20, F, 1.65> using K-Nearest Neighbor algorithm with K=4 and a simple majority voting. To calculate distances between each two records, we are required to consider both Gender and Height attributes . For the gender attribute, assume the following distance functions d(F, F) =d(M, M) = 0; d(F, M)=d(M, F)= 0.2 Using the Manhattan Distance, find the 4 nearest neighbors to the new item, and classify it based on a majority voting. In your solution, specify the neighbors, and calculate the distance between the new item and each neighbor. 1 2...
View Full Document

This note was uploaded on 02/06/2011 for the course ORIE 474 taught by Professor Apanasovich during the Spring '07 term at Cornell University (Engineering School).

Page1 / 2

hw5 - item <P20, F, 1.65> using K-Nearest Neighbor...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online