ML Club Video: Linear Regression to Neural Networks
In this ML club session, we go from Linear Regression to Neural Networks in just one go!
Linear Regression is all about lines of best fit for a given dataset. But how do we find lines of best fit? Here is a quick answer:
- Start with a random line
- For each data point in dataset
a) Find how “close” the line is to the point
b) Depending on how close/far the line is, move the line a step towards the point
Step 2 can be repeated multiple times (called epochs)
In 3D, a “line of best fit” is a plane of best fit. And in higher dimensions? That’s when we get into neural networks. And once we represent our models as networks, we can start doing high-dimensional curves of best fit.
But how do neural networks get trained? Why use neural networks? Watch the video to know more!
If the embedded video above does not work, here’s the link: https://drive.google.com/file/d/17N08DVvCioo-3QDfLxhjkg7XwopFpY7W/view?usp=sharing