Ranking Forests using Neural Networks – We present the task of clustering (a.k.a. clustering) from synthetic data. We apply the notion of clustering (named clusters) to the real world data sets, and propose a method for learning a classifier by a neural network trained from a real data set. The key idea of our approach is a fully feed-forward-decision-learning (FFD) algorithm that exploits information flow between cluster predictions, that will be used to decide whether to assign or not. The proposed method takes a neural network as input and learns a classifier based on a feature set associated to each node, via a neural network network trained by a prior activation function or weight set, which is then fed directly to a FDD algorithm. We apply our method to a real world dataset where the number of nodes in an environment (e.g., homes, parks, airports) increased over three-fold with the use of the neighborhood structure representation (i.e., the location of the user). By using the data, we propose a new clustering algorithm using the neighborhood structure representation.

We present the results of a large-scale, well-studied and statistically studied experiment on the problem of multi-modal neural network (NN) classification using a single-modality network (i.e., multi-modal neural models with different classes). An interesting result of this experiment is that we can get the state-of-the-art performance on the ILSVRC2011 problem (which is a typical multi-modal neural model) on single-modal neural models, outperforming state-of-the-art results on the CIFAR-10 and ILSVRC 2012 benchmark tests. The state-of-the-art results on the benchmark CIFAR-10 task are much better than others, and a new benchmark for the CIFAR-10 task is also provided.

Learning for Visual Control over Indoor Scenes

Hierarchical Gaussian Process Models

Ranking Forests using Neural Networks

Multiclass Super-Resolution with Conditional Generative Adversarial Networks

Hierarchy in a fuzzy networkWe present the results of a large-scale, well-studied and statistically studied experiment on the problem of multi-modal neural network (NN) classification using a single-modality network (i.e., multi-modal neural models with different classes). An interesting result of this experiment is that we can get the state-of-the-art performance on the ILSVRC2011 problem (which is a typical multi-modal neural model) on single-modal neural models, outperforming state-of-the-art results on the CIFAR-10 and ILSVRC 2012 benchmark tests. The state-of-the-art results on the benchmark CIFAR-10 task are much better than others, and a new benchmark for the CIFAR-10 task is also provided.