Understanding Idea behind Full Backpropogation

Thu, 02 Jul 2026 18:14:45 +0000

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 learned how to calculate the gradient of the last bias in a neural network.

Now we will explore how gradients flow through the entire network and how to calculate the weights of previous layers.

How to calculate weights

Now we will calculate weights of the previous layer

The challenge is that the loss function does not directly depend on these earlier weights.

For example, consider a weight (w1 and w2 are already calculated ) in a hidden layer.

Changing (w3 and w4):

Changes the hidden neuron output.
Changes the output neuron input.
Changes the final prediction.
Changes the loss.

So there is an indirect relationship between the weight and the loss.

This is exactly why we need the chain rule.

Conclusion

Similar to previous calculation we should also calculate for all weights and biases using chain rule and gradient descent.

Any feedback or contributors are welcome! It’s online, source-available, and ready for anyone to use.

⭐ Star git-lrc on GitHub

How to work with channels?

Thu, 02 Apr 2026 00:25:43 +0000

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 Us to help devs discover the project. Do give it a try and share your feedback for improving the product.

In this article we will understand how to work with channels.

What is a channel? Why it is needed?

Channels are used to pass data between goroutines.
They are a way to synchronize the flow of data between different parts of a program.

When to use channels?

Let's see the example below.

Have 2 goroutines to calculate the sum of an array.

First, we will calculate the sum of the first half of the array.

Second, we will calculate the sum of the second half of the array.

package main

import (
    "fmt"
)

func add(a []int, c chan int) {
    sum := 0
    for _, v := range a {
        sum += v
    }
    c <- sum
}

func main() {
    a := []int{7, 2, 8, -9, 4, 0}

    c1 := make(chan int)
    go add(a[:len(a)/2], c1)

    c2 := make(chan int)
    go add(a[len(a)/2:], c2)

    x, y := <-c1, <-c2
    fmt.Println(x, y, x+y)
}

Finally, we will print the sum of the first half and the second half of the array.

Output:

gk@jarvis:~/exp/code/rd/go-exmaple$ go run main.go 
17 -5 12

Conclusion

Channels play a crucial role in concurrent programming by enabling safe communication and synchronization between goroutines.
This makes it easier to build concurrent programs that are both efficient and safe.

Any feedback or contributors are welcome! It’s online, source-available, and ready for anyone to use.
⭐ Star it on GitHub: https://github.com/HexmosTech/git-lrc

Coder Legion - Recent posts tagged calculate

Understanding Idea behind Full Backpropogation

How to calculate weights

Conclusion

How to work with channels?

What is a channel? Why it is needed?

When to use channels?

Conclusion