Day 39 - Checking out other courses (most are 2+ years old)

January 1st - Checking out some other AI/ML courses

• #3 Machine Learning Specialization [Course 1, Week 1, Lesson 2]

• Switched over to Coursera Deep Learning and Neural Networks

  • Much better walk through of the concepts forward and backward propagation – I understood these concepts much better this time around.

  • What you need to remember:

    • np.exp(x) works for any np.array x and applies the exponential function to every coordinate
    • the sigmoid function and its gradient
    • image2vector is commonly used in deep learning
    • np.reshape is widely used. In the future, you’ll see that keeping your matrix/vector dimensions straight will go toward eliminating a lot of bugs.
    • numpy has efficient built-in functions
    • broadcasting is extremely useful
    • Vectorization is very important in deep learning. It provides computational efficiency and clarity.
    • You have reviewed the L1 and L2 loss.
    • You are familiar with many numpy functions such as np.sum, np.dot, np.multiply, np.maximum, etc…
• One common preprocessing step in machine learning is to center and standardize your dataset, meaning that you substract the mean of the whole numpy array from each example, and then divide each example by the standard deviation of the whole numpy array. But for picture datasets, it is simpler and more convenient and works almost as well to just divide every row of the dataset by 255 (the maximum value of a pixel channel).