Where can I start learning TensorFlow for Machine Learning with Python?

Machine Learning is creating a huge impact on society. Today, almost every industry is using Machine Learning to optimize processes leading to cost reductions and time savings.

Seeing this rapid growth of Machine Learning, tech companies are investing heavily in it. Google played it smart by open-sourcing its Machine Learning platform - TensorFlow. Today, it has become one of the most popular Machine Learning libraries.

Here are 2 key prerequisites for applying Machine Learning using Tensorflow:

  1. Basics of Python programming: it is expected that you are familiar with the basics of Python. This includes the syntax and constructs like variables, constants, if-else, for/while loops, etc. You can take any basic Python course for the same. You should definitely check out the Programming Foundations with Python course on Udacity.

  2. Basic knowledge of Machine Learning: this is kind of obvious because Tensorflow won’t magically do the ML work for you. You are supposed to write your own ML algorithms using Tensorflow and therefore, you should have knowledge of some common ML algorithms like Linear Regression, Logistic Regression, SVM, kNN, and of course Neural Networks. A great starting point would be Andrew Ng’s course on Coursera. The course would teach you the basics of ML using Octave. Don’t worry, Octave is easy and would help you develop the right foundations.

Once you are through with the basics of Python and ML, you can start with Tensorflow. Tensorflow tutorial is a great place to start off with. They have given quite a few examples. However, the overall tutorial is a bit unorganized and may be slightly overwhelming for a beginner.

Lately, I have been taking courses on Eduonix and I found a great course on Machine Learning With TensorFlow The Practical Guide. The best part about this course is that covers the basics of Machine Learning as well, so you might want to skip Andrew Ng’s course. Moreover, the course has several codes and projects which will help you put something on your resume as well. You can not only mention completing the course but also put the projects on your resume which is certainly going to create an impact.

I would say that for Machine Learning, you should always keep in mind 2 things:

  1. Machine Learning is like swimming. You learn it by applying it. You can’t just read theory and become an expert. Solve a lot of problems and take a lot of projects.

  2. To build your resume around Data Science/Machine Learning, take courses that help you develop projects. You can then showcase these projects on your resume and moreover, talk about them in your interview. That will create a far more impact on the interviewer than just saying I did a course on ML.