Deep learning specialization, started course 1 [Post #24, Day 48]

I started the DeepLearning.AI, Deep Learning Specialization program led by Andrew Ng two days ago. I am doing Course 1 – Neural Networks and Deep Learning – now. I have just started Week 3 of this course. Each week takes about one day, however I haven't paid the Coursera fee yet so I don't have access to the graded assignments.

These are the courses making up the Deep Learning Specialization program:

  1. Neural networks and deep learning
    • Introduction to deep learning
    • Neural networks basics
    • Shallow neural networks
    • Deep neural networks
  2. Improving deep neural networks: hyperparameter tuning, regularization and optimization
    • Practical aspects of deep learning
    • Optimization algorithms
    • Hyperparameter tuning, batch normalization and programming frameworks
  3. Structuring your machine learning project
  4. Convolutional neural networks
  5. Natural language processing: building sequence models

It has been a really good revision of material I learned in the Z2H course so far. It's good timing to have some revision, but also hearing things presented slightly differently but still consistent with what I learned before has deepened my understanding I believe. Like one example is we did a simple forward and backward pass, I then realized that tells me if I increase one of the parameters (e.g. weight) at the beginning of the neural net, exactly the effect it'll have on the loss function at the end. That was a cool concrete realization moment. I'm glad in the Z2H series that Andrej showed the equation on Wikipedia for a derivative with the nudge (limit as h approaches 0), that really helped my understanding of doing the backpropagation derivatives, and I didn't quite get that part in Andrew's lecture. So there are strong things in both, which works well when combined together.

And some things happening outside of my online learning. I am attending a Code & Coffee event in Newark this afternoon.

More from A Civil Engineer to AI Software Engineer 🤖
All posts