Learning from Continuous Events with the Gated Recurrent Neural Network – We present a novel deep-learning technique to automatically learn the spatial location of objects in a scene, which is based on Recurrent Neural Networks (RNN) and can achieve high accuracies by learning the object location from a large set of object instances. In this work, we provide state-of-the-art classification accuracies at an accuracy of 10.81%. Our method can be embedded into many different RNN architectures and can be applied to datasets. We demonstrate the effectiveness of our approach in a supervised task where we use Gated Recurrent Neural Network (GRNN) to extract object-oriented objects and then apply the method at the scene.

We propose a new approach for training a Bayesian network for automatic speech recognition from a corpus of speech utterances of different languages. Our approach is based on the use of neural networks to learn a hierarchical Bayesian network architecture that learns a latent state structure with an internal discriminator to predict the speaker’s utterance structure. Our model also learns the internal state structure by using the hidden hidden units of a Bayesian network model for this task. The latent state structure is represented by a corpus of sentences (both English and Dutch spoken) and it can be inferred from these sentences.

An Efficient Stochastic Graph-based Clustering Scheme for Online Learning of Sparse Clustered Event Representations

Fast Low-Rank Matrix Estimation for High-Dimensional Text Classification

Learning from Continuous Events with the Gated Recurrent Neural Network

A Nonparametric Coarse-Graining Approach to Image Denoising

Learning a Hierarchical Bayesian Network Model for Automated Speech RecognitionWe propose a new approach for training a Bayesian network for automatic speech recognition from a corpus of speech utterances of different languages. Our approach is based on the use of neural networks to learn a hierarchical Bayesian network architecture that learns a latent state structure with an internal discriminator to predict the speaker’s utterance structure. Our model also learns the internal state structure by using the hidden hidden units of a Bayesian network model for this task. The latent state structure is represented by a corpus of sentences (both English and Dutch spoken) and it can be inferred from these sentences.