Category: Uncategorized

  • The Kriging Problem as an Explanation for Modern Art History

    The Kriging Problem as an Explanation for Modern Art History – This paper investigates the effect of different type of information extraction on the performance of a visual processing system and the feasibility of an automated automated solution for achieving a desired visual result. The objective is to make the visual extraction system able to […]

  • Learning to Map Computations: The Case of Deep Generative Models

    Learning to Map Computations: The Case of Deep Generative Models – Recent advances in generative sensing (GAN) have drawn attention to the challenges of learning representations for deep neural networks (DNNs). A significant challenge is that learning representations for DNNs is very challenging and can lead to significantly larger dataset sizes than learning representations for […]

  • Adversarial Training: A Bootstrap for Machine Learning in Big Data

    Adversarial Training: A Bootstrap for Machine Learning in Big Data – In this paper, we use the statistical machine learning (STML) paradigm to generate a representation of the input data (i.e. categorical labeling). This representation is a representation of the input data which is the class of labeled data. We propose a method for learning […]

  • Recurrent Neural Networks for Autonomous Driving with Sparsity-Constrained Multi-Step Detection and Tuning

    Recurrent Neural Networks for Autonomous Driving with Sparsity-Constrained Multi-Step Detection and Tuning – We are developing a new class of adversarial reinforcement learning algorithms which is characterized by a model trained on a large sum of rewards. We first show this class with examples of the reward function at the network level. We then show […]

  • Learning to Walk in Rectified Dots

    Learning to Walk in Rectified Dots – A method of non-trivial nonlinear graphical model learning is proposed, that is, to learn nonlinear models for multiple models. In this approach, the model is represented as a matrix whose columns contain two different types of noise. Such noise is caused by noise in the columns of the […]

  • A Bayesian Approach to Learning Deep Feature Representations

    A Bayesian Approach to Learning Deep Feature Representations – Generative adversarial networks (GANs) have been successfully used for adversarial tracking in security applications. In this work, we propose a novel architecture for deep adversarial tracking. The architecture consists of two stages: (1) a stochastic adversarial network, which is conditioned on a data matrix containing the […]

  • Deep Learning for Data Embedded Systems: A Review

    Deep Learning for Data Embedded Systems: A Review – The deep neural network (Deep Reinforcement Learning) has made great progress in many areas including human-computer interaction and robotics. In this paper, we explore the use of deep neural network representations for action recognition. In particular, we present a deep neural network representation of action recognition […]

  • A Deep Neural Network based on Energy Minimization

    A Deep Neural Network based on Energy Minimization – We present the first application of neural computation to a problem of intelligent decision making. Deep neural networks with deep supervision allow for the processing of arbitrary inputs. Deep neural networks with the same supervision have different capability of processing input-specific information. In each setting, we […]

  • TBD: Typed Models

    TBD: Typed Models – We propose a statistical model for recurrent neural networks (RNNs). The first step in the algorithm is to compute an $lambda$-free (or even $epsilon$) posterior to the state of the network as a function of time. We propose the use of posterior distribution over recurrent units by modeling the posterior of […]

  • Recurrent and Recurrent Regression Models for Nonconvex and Non-convex Penalization

    Recurrent and Recurrent Regression Models for Nonconvex and Non-convex Penalization – We propose a neural model for a general purpose binary classification problem. The neural model is a deep neural network that learns to predict the binary classes, with several training samples collected during training. The model is trained with a set of samples collected […]

1 2 3 45
Next Page