Types of machine learning -Supervised Machine Learning
Now that I already talked about what exactly machine learning is, (If you’d like to refer here is the link https://abbynyakara.medium.com/deciphering-machine-learning-2d313e25849b
Now lets delve into the different types of machine learning. Broadly, these can be categorized as Supervised and unsupervised learning.
(I know there is reinforcement learning but i will leave that out for now. I shall revisit this in a later blog.)
When talking of Supervised learning, as the word supervised suggests, we have a reference point.
If you refer to the image at the top of the blog, you see that the data we are feeding into the machine is in the form of shapes(labeled data). This data has labels. The labels tell what each shape is. So in that case, if we were to give the machine a certain image that is not labelled, it can comb through and check if it resembles a triangle or a rectangle or hexagon and give the output. This is the principle of supervised machine learning: Learn from the past to predict the future.
Other people also refer to it as predictive analysis. Basically we are using the past information that we know to predict the future.
When building models under supervised machine learning, some of the models we can talk of include
- Linear regression Models
- Logistic regression Models
- Neural Networks (also referred to as Deep learning)
P/S: Examples of such models and the mathematics behind them will be posted on my github as we progress
