Backpropagation
<p>The term<em> backpropagation</em>, short for “backward propagation of errors,” is a supervised learning algorithm used to minimize errors in predictions made by neural networks.</p>
<p>In principle, Backpropagation is a chain-rule application that can be used to compute gradients of loss functions in relation to model parameters.<br />
The mechanism operates in two main phases:</p>
<p>The <strong>forward pass</strong> and the <strong>backward pass</strong>.</p>
<p><a href="https://pub.towardsai.net/backpropagation-2eeb25201095"><strong>Click Here</strong></a></p>