So I recently made a classifier for the MNIST handwritten digits dataset using PyTorch and later, after celebrating for a while, I thought to myself, “Can I recreate the same model in vanilla python?” Of course, I was going to use NumPy for this. Instead of trying to replicate NumPy’s beautiful matrix multiplication, my purpose here was to gain a better understanding of the model by reinventing the wheel.
I challenged myself to make a similar classifier in numpy and learn some of the core concepts of Deep Learning along the way. You can find the code in my GitHub repository.
#deep-learning #python #numpy #backpropagation #mnist-dataset