Week 4
I have finished the first part of the Coursera machine learning course I have started taking. In this part of the course by Andrew Ng, I learned about the history and purpose of machine learning, the difference between supervised and unsupervised learning, model and cost functions, and linear algebra.
I will start working on the next section of the machine learning course. This includes doing some actual programming assignments in the Octave or Matlab programming languages.
In addition, I have tried some different algorithms – ZeroR, DecisionStump, and M5P – on the Kaggle data sets, to see if any of them work better than IBk. However, these algorithms seem to have about the same error rate. As they are still a small sample, I will continue looking for new algorithms in the hopes of finding one that makes fewer errors.
It’s awesome that you’ve finished the first part of the course. I also took that course earlier, and truly enjoyed leveraging the simplicity, beauty, and computational excellence of MATLAB.
I would highly recommend doing the programming assignments on the course as you progress through the lectures. They can reinforce what you learned and serve as important indicators of understanding. Also, they are super cool!
I wish you luck with the rest of your project, and I can’t wait to see the algorithms you try next time!
I completely agree with what Sahil said above. The programming assignments are important! I’m interested to see which algorithm will make the least errors.
What kind of data are you going to feed your machine? And how will your machine also take into account the several social factors that factor into success? Students struggling with mental health might still achieve high scores, but they’re still at risk in the future.