Section Recap
Introduction
This short lesson summarizes the topics we covered in section 14 and why they'll be important to you as a data scientist.
Objectives
You will be able to:
- Understand and explain what was covered in this section
- Understand and explain why this section will help you become a data scientist
Key Takeaways
In this section, we both learned how to traverse a cost function graph to find the local minima to solve a linear regression by using a gradient descent and covered some of the foundational calculus that will help you to understand many of the other machine learning models you'll encounter as a professional data scientist. Key takeaways include:
- A derivative is the "instantaneous rate of change" of a function - or it can be thought of as the "slope of the curve" at a point in time
- A derivative can also be thought of as a special case of the rate of change over a period of time - as that period of time tends to zero.
- If you calculate the rate of change over a period of time and keep reducing the period of time, it usually tends to a limit - which is the value of that derivative
- The power rule, constant factor rule and addition rule are key tools for calculating derivatives for various kinds of functions
- The chain rule can be a useful tool for calculating the derivate of a complex function
- A derivative can be useful for identifying local maxima or minima as in both cases, the derviative tends to zero
- A cost curve can be used to plot the values of a cost function (in the case of linear regression) for various values of offset and slope for the best fit line.
- A gradient descent can be used to move towards the local minima on the cost curve and thus the ideal values for offset and slope to minimize the selected cost function