The final goal of cuSAE is to train a sparse autoencoder to classify the MNIST dataset, while using CUDA C to implement expensive computations.
First we need to add MATLAB code that imports the dataset and uses the (CUDA C) function that computes the cost and the gradients used for backpropagation.
The final goal of cuSAE is to train a sparse autoencoder to classify the MNIST dataset, while using CUDA C to implement expensive computations.
First we need to add MATLAB code that imports the dataset and uses the (CUDA C) function that computes the cost and the gradients used for backpropagation.