Deep Neural Maps
This is an incremental method for researchers in unsupervised learning and visualization, offering a new approach to combine deep networks with self-organizing maps.
The paper tackled unsupervised representation learning and visualization by introducing Deep Neural Maps (DNM), which jointly learns an embedding and maps it to a 2D lattice, showing that DNM learns efficient representations reflecting class characteristics on MNIST and COIL-20 datasets.
We introduce a new unsupervised representation learning and visualization using deep convolutional networks and self organizing maps called Deep Neural Maps (DNM). DNM jointly learns an embedding of the input data and a mapping from the embedding space to a two-dimensional lattice. We compare visualizations of DNM with those of t-SNE and LLE on the MNIST and COIL-20 data sets. Our experiments show that the DNM can learn efficient representations of the input data, which reflects characteristics of each class. This is shown via back-projecting the neurons of the map on the data space.