Loss Function

How do we know if our neural network is doing a good job? We need a score to measure its performance. A Loss Function (or Cost Function) quantifies the error between the network’s prediction and the actual target.

Different tasks require different loss functions. Here, y^\hat{y} represents the predicted value (our activation output aa) and yy represents the true target.

L=1ni=1ny(i)y^(i)L = \frac{1}{n} \sum_{i=1}^{n} |y^{(i)} - \hat{y}^{(i)}| L=1ni=1nc=1Cyc(i)log(y^c(i))L = -\frac{1}{n} \sum_{i=1}^{n} \sum_{c=1}^{C} y_{c}^{(i)} \log(\hat{y}_{c}^{(i)})

    Mike 3.0

    Send a message to start the chat!

    You can ask the bot anything about me and it will help to find the relevant information!

    Try asking: