Machine Learning is one of the fastest growing fields. Top tech companies like Google, Facebook, Amazon, Apple, and Microsoft are investing heavily in Machine Learning. For us, it is a great opportunity because not only does it open new avenues for learning but also it creates a lot of high-paying jobs and internships which we can grab.
Hold Down your horses for a bit. Don't start learning Python/R just yet, before that you need to learn some mathematical concepts in order to understand what's happening under the hood of a machine learning algorithm and it'll help you to write machine learning algorithms by yourself. Machine Learning can be divided as 65% Mathematics, 25% Algorithm design, 10% data preprocessing. Diving the section of Mathematics for machine learning we have:
Today's most machine learning algorithms are implemented in python or R. For Machine Learning, it is highly recommended that you use Python as the programming language. Python has excellent libraries for Machine Learning and it integrates well with quite a few web-frameworks.
So here comes the interesting part diving into machine learning algorithm and implementing them on the data set to do analysis. By far, the best known introductory course on Machine Learning is Andrew Ng’s Course on Coursera, but it uses octave as primary language but you can implement algorithms in python parallely. If you find the course exhausting because of octave you can refer to the other courses below
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources.Familiarity with other frameworks gives you a headstart over others. However, out of all frameworks, tensorflow is ahead of all others (due to high demand in Industries and compatibility with other languages.
To get some great project ideas on Machine Learning, you can visit Kaggle. Kaggle contains a large number of datasets on which you can implement your own algorithms. Google has also launched a repository of ML Datasets. Each dataset is a project opportunity.
After you're done with the basics you can refer to the following to explore more into the field of machine learning.