Read on Twitter
Do you have a hammer that you use to slice a pie?
Probably not.
This is no different with what problems that Machine Learning can solve. Like other tools, there are what it is suited for and what it is not.
Thread
Probably not.
This is no different with what problems that Machine Learning can solve. Like other tools, there are what it is suited for and what it is not.
Thread
ML is suitable for problems which are:
Very clear and simple to formulate. These include yes or no question (eg: email is yes or not spam), or predicting a single variable such as price of house given the number of bedrooms, region,...
Very clear and simple to formulate. These include yes or no question (eg: email is yes or not spam), or predicting a single variable such as price of house given the number of bedrooms, region,...
Hard to be solved by traditional programming: How many rules would you have write when implementing a face detection algorithm without using machine learning? That would be a complex program and less accurate at the end. How about sentiment analysis?
Deep and resonate some forms of intelligence. Example of this is often in machine vision and language processing. Machine Learning (Deep neural networks specifically) has shown potential in object recognition & detection, voice synthesis, machine translation, etc...
However, ML is not suited for tasks:
Which are expected to change the world in matter of hours
Which are expected to change the world without good data
Which can be solved easily with traditional programming
Whose patterns are very clear and constant
Which are expected to change the world in matter of hours Which are expected to change the world without good dataWhich can be solved easily with traditional programmingWhose patterns are very clear and constant
