Ans: For both sparse categorical cross entropy and categorical cross entropy have same loss functions but only difference is the format.
J(w)=−1N∑i=1N[yilog(y^i)+(1−yi)log(1−y^i)]
Where
w refers to the model parameters, e.g. weights of the neural network
yi is the true label
yi^ is the predicted label
If your Yi’s are one-hot encoded, use categorical cross entropy. But if your Yi’s are integers, use sparse cross entropy. The usage entirely depends on loading the dataset. Advantage of using sparse categorical cross entropy is, it saves time in memory as well as speed up the computation process.