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.
In the previous article, we discussed how action potentials are defined.
Let's take a simple example and plot a graph.
Using Softplus as the Activation Function
For our initial example of dosage, we can take Softplus as an activation function.
Now let's find the dosage and y values based on the formula:
( Dosage x -34.4 ) + 2.14
For dosage : 0
( 0 x -34.4 ) + 2.14 = 2.14
For dosage : 0.1
( 0.1 x -34.4 ) + 2.14 = -3.44 + 2.14 = -1.3
Now let's multiply all the values calculated in the top-most hidden layer with -1.3.
For dosage : 0
2.14 x -1.3 = -2.782
For dosage : 0.1
-1.3 x -1.3 = 1.69
Similar calculations can be done for the top-most node values.
Calculating the Bottom Node
Now for the bottom-most node:
( Dosage x -2.52 ) + 1.29
For dosage : 0
( 0 x -2.52 ) + 1.29 = 1.29
For dosage : 0.1
( 0.1 x -2.52 ) + 1.29 = -0.252 + 1.29 = 1.038
Now multiply all the values calculated in the bottom-most hidden layer with 2.28.
For dosage : 0
1.29 x 2.28 = 2.94
For dosage : 0.1
1.038 x 2.28 = 2.366
Combining Both Node Results
From both the top and bottom node results, we add them together.
Finally, we subtract 0.5690 from the final value.
Here is the final prediction made by the neural network.
Weights Used in the Neural Network
These are the weights:
Bias Values Used in the Neural Network
These are the bias values:
Support git-lrc
Any feedback or contributors are welcome! It’s online, source-available, and ready for anyone to use.
⭐ Star git-lrc on GitHub