Completed the Machine Learning course by Stanford University!

I could completed the Machine Learning course by Stanford University! Yay!

I started in April, and I could finish it at the end of June. So It took about 3 months.

(Please refer to the entry, which was written in the beginning => Started to study Coursera Machine Learning course by Stanford Univ.)

Course Certificate

Pros

  • I could study whole general machine learning algorithms.
  • By submitting the programming assignments, I could understand deeper.
  • I could keep my motivation very high to understand the class because I can’t complete the assignments if I don’t understand it.
  • The great explanation from the teacher Mr. Andrew Ng.
  • The logic is explained with mathematics, and it was great he explained very intuitive.
  • Coursera issues the course certificate (it’s not free but only $89 and it worths)

Cons

  • Unfamiliar programming language “Octave”. But Octave is quite intuitive for calculation.
  • A bit hard to submit the programming assignment every week, but this became good training.
  • Takes time to get remember linear algebra, matrix, partial differentiation, etc…
  • I’m not familiar with mathematical terms in English. (I could study many new words)

What I studied

  • Cost Function
  • Gradient Descent
  • Linear Regression
  • Logistic Regression
  • Neural Networks
  • Backpropagation
  • Evaluating a Learning Algorithm
  • SVM (Support Vector Machines)
  • Unsupervised Learning
  • Dimensionality Reduction
  • Anomaly Detection, Recommender Systems
  • Large Scale Machine Learning
  • Application Example: Photo OCR

It was really great that Mr. Andrew Ng explains very intuitive. I could imagine how the equation works and what the logic is. This is very first time for me to study something online, I found it’s very fun and I like it.

It was very good rhythm to study and submit the assignment on the weekend, I’m thinking to start new course.

Well if you want to study Machine Learning, I recommend this course definitely.

@takp