You’ve just completed Introduction to Machine Learning. To recap, here are a few of the main takeaways from this course:
When organizations apply data science, they can find ways to solve many problems and improve their services and products.
A machine learns rules when it is provided data, such as past experiences and answers, as inputs. These rules form the basis for algorithms, and algorithms form the basis of machine learning.
When an algorithm is fed inputs of “x” along with known outcomes of “y”, it can plot the values. This plot results in a line where the equation is y = mx + b. The constant value “m” is the slope or gradient of the line, and the constant “b” is the y-intercept value.
Once the algorithm determines the values of the slope and intercept, it is said to be “trained” and it can begin making predictions on new, unseen data (also known as observations or examples).
Machine learning takes its inspiration from the way humans learn.
Machine learning can be supervised or unsupervised, that is, it can use labeled data or unlabeled data.
The goal of supervised learning, using labeled data, is to learn a function that maps an input to an output.
The goal of unsupervised learning, using unlabeled data, is to find patterns and similarities in the data set.
Finally, we learned about different types of classification, regression, and clustering algorithms.