Trained LeNet5 on MNIST with SGD and ADAM
————->a)LeNet5 on MNIST with SGD:
—————————>Effect of training loss vs. Batch size for a fixed learning rate
—————————>Effect of training loss vs. Learning rate for a fixed Batch size
————->b)LeNet5 on MNIST with ADAM
—————————>Effect of training loss vs. Batch size for a fixed learning rate
—————————>Effect of training loss vs. Learning rate for a fixed Batch size