Bibliography:

1. ​ Gradients without Backpropagation

2. ​ MLP-Mixer: An all-MLP Architecture for Vision

3. ​ https://arxiv.org/abs/2105.08050

4. Wikipedia Bibliography:

   1. ​ Backpropagation

   2. ​ Variance

   3. ​ Loss Function

   4. ​ MNIST Database

   5. ​ CIFAR-10

   6. ​ ImageNet