Machine Learning Crash Course From Google

We’ve talked a lot about machine learning lately. People use it to create and recognize speech, computer vision and even radio signals. If you still need to make progress on the learning curve, you might be interested in a new free Google course with TensorFlow.

Of course, we’ve already covered tutorials for TensorFlow, but this is structured as a 15-hour class with 25 hours and 40 exercises. Of course, it’s also out of the horse’s mouth, so to speak. Google says the class will answer questions like:

  1. How does machine learning differ from traditional programming?
  2. What is a loss, and how do I measure it?
  3. How does gradient descent work?
  4. How do I determine whether my model is effective?
  5. How do I represent my data so that a program can learn from it?
  6. How do I build a deep neural network?

Google says that you have to be an expert in introductory algebra and that higher math can be helpful, but not essential. You should also know something about programming with some familiarity with Python. The exercises are executed in your browser, so you do not need exotic settings. There are also some tools that suggest tutorials if you do not know them anymore. For example, the pandas and bash library are included in this list.

If you’re really serious, Google has lots of educational resources to keep you going. If you learn by a better example, you can try to undress.