Introduction to TensorFlow
Google
Quite a lot stuff of TensorFlow was distilled into this course, from the basics to advanced techniques. I guess some topics probably will make beginners confused, but will strike a chord with experienced developers.
The course first introduced the layers of API, the very basic tensor and Variable. Then put much effort on input data pipeline, datasets, feature columns, etc. I can not agree more that it is very important, since usually data extraction, analysis and preparation consume much of time and are critical to the success of the entire solution.
Next, the course focused on building the model. It covered the Activation function and demonstrated how easy it is to build complicated models using Keras Sequential and Functional API. The Wide and Deep Neural Networks was really a nice touch, I love it. Lastly the course covered overfitting, and how to use regularization, early-stopping and dropout to balance the loss of data and model complexity.
The course contains a dozen of programing assignments (with solutions) helping you understand all topics. I have been using TensorFlow for years, but I still learned something new and interesting.
Quick Recap
My Certificate
https://coursera.org/share/086460cdddf5081b0d62d140e952bb63
I am Kesler Zhu, thank you for visiting my website. Checkout more course reviews at https://KZHU.ai