Meral Posted June 25, 2017 Report Share Posted June 25, 2017 Hey guys, I will start writing my extended essay this month and I am struggling to decide a question for my EE. Here are the two questions that I came up with. What do you think about them? I'm planning to study artificial intelligence so these topics are based on machine learning. what is the relation for linear regression between the size of data set and success rate of the algorithm? I will have various types of data sets and I will decide which is better in a way that I can find a theta that satisfies my data most. To what extent an anomaly in the data set can effect the outcome of linear regression and can it be detect by anomaly detection algorithms? and finding the balance between anomaly and regression outcome This is the one I like more:) given a controlled data set, I will place anomalies and look at its effect on the theta I find and success rate. Then I will use anomaly detection and remove those anomalies. I will compare the success rate and theta with and without anomaly detection. Reply Link to post Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.