k-Sparse Autoencoders
This addresses the need for efficient sparse representation learning in machine learning, offering a simple and fast method suitable for large-scale problems, though it is incremental as it builds on existing autoencoder and sparsity concepts.
The paper tackled the problem of improving classification performance by learning sparse representations, proposing the k-sparse autoencoder that keeps only the k highest activities in hidden layers, and found it achieved better results than denoising autoencoders, dropout-trained networks, and RBMs on MNIST and NORB datasets.
Recently, it has been observed that when representations are learnt in a way that encourages sparsity, improved performance is obtained on classification tasks. These methods involve combinations of activation functions, sampling steps and different kinds of penalties. To investigate the effectiveness of sparsity by itself, we propose the k-sparse autoencoder, which is an autoencoder with linear activation function, where in hidden layers only the k highest activities are kept. When applied to the MNIST and NORB datasets, we find that this method achieves better classification results than denoising autoencoders, networks trained with dropout, and RBMs. k-sparse autoencoders are simple to train and the encoding stage is very fast, making them well-suited to large problem sizes, where conventional sparse coding algorithms cannot be applied.