I was curious about the real influence of parameter on CNN training result. And I want to see if the result aligns with the estimation. I used the MNIST dataset and tune the parameters based on an old network called LeNet-5. CNN Layer The CNN layout is mostly the same as LeNet-5, with small modifications, for example, adding Dropout to avoid overfitting. The reason that I used LeNet-5 is mostly that it’s small and can train at a super fast speed with little GPU requirement[…]
Continue reading …