Hello, I'm Ganesh. I'm building git-lrc, an AI code reviewer that runs on every commit. It is free, unlimited, and source-available on GitHub. Star git-lrc on GitHub to help more developers discover the project. Do give it a try and share your feedback for improving the product.
If you have learned differentiation in your school/college days, then most of us have learnt differentiation formula
But we couldn't just understand how this was actually defined. Let's just plot on a graph and see.
Practicality of Differentiation
Let's take an example of velocity and acceleration.
Whenever a ball is thrown in the air, it will travel in a curved path, which is also called parabolic motion.
Initially, based on acceleration, the velocity will be a peak, and at the highest point it will be zero, and again it increases while coming down.
This is how it looks:
Similarly, we can plot it as this.
If we differentiate it, we would get a straight line in the graph, also known as a slope.
So basically from this graph we can get the exact velocity value at this specific point of acceleration.
This is mainly used in physics and mechanical engineering, where we need the exact value of slope at a specific point.
Why it matters in neural networks?
In a neural network, we use the chain rule to derive the weights and bias.
Will talk about this in detail with proper examples.
Any feedback or contributors are welcome! It’s online, source-available, and ready for anyone to use.