ML is one of the industry-leading sectors and evergrowing field. It opens up several aspects of modern engineering and engineering paradigms that deal with continuous "learning" and "building" models that fit and solve the problem under consideration accurately or with decent approximations.
Machine Learning involves good amount of mathematics and there are several resources out there that shall help to understand the subject at great depth. The following resources shall be sufficient to get started with ML:
-
Machine Learning, Andrew Ng, Standford, Coursera course : Audit this course for getting a complete introduction to Machine Learning and its paradigms. This will be an excellent base for clearing the foundation.
-
Mathematics for Machine Learning : For those who prefer understanding the extreme mathematics that Machine Learning encompasses. Useful for folks interested in the Research Domain.
-
IBM Machine Learning Specialization : Audit the courses under this specialization if one is interested in learning specific topics of Machine Learning like:
- Data Analysis for ML.
- Supervised Learning using the Regression Paradigm
- Supervised Learning using Classification
- Unsupervised Learning
- Deep Learning and Reinforced Learning
- Specialized Models: Time Series and Survival Analysis
-
Neural Networks and Deep Learning Tour : A free online web-book would help in grasping specifics of Neural Networks and Deep Learning Principles
ML is a field that requires constant exposure to the world to attain the latest new and developments in the sector involving new technologies, new techniques et cetra. Machine Learning Articles by Massachusetts Institute of Technology, ML Articles, IEEE Spectrum both provide for latest developement digests.