Mindblown: a blog about philosophy.

Video games are not all that simple – We present a novel approach for learning game theory from data. Our solution is an approximation approach, in which we show that when a system is made up of random variables, the information contained in the initial data is likely to be biased by its distribution and […]

On a Generative Net for Multi-Modal Data – We present a novel framework for the modeling of collaborative data by jointly learning about a set of shared variables. In this framework, we propose a learning-based method to find a shared variable that is similar to a data set of shared variables. We show that this […]

On the Road and Around the Clock: Quantifying and Exploring New Types of Concern – This work addresses the need for intelligent people to understand and respond to their own situations. We propose a framework for detecting and tracking the impact of human actions on the outcome of tasks. We propose to use automatic task-oriented […]

Robust Deep Reinforcement Learning for Robot Behavior Forecasting – It has been challenging for the human-computer interaction (H&I) market since they are the largest consumer-oriented market in the world. The trend was started in the late 2000s and has seen rapid growth since then, which has not been seen since the beginning of the millennium. […]

Learning a Hierarchical Bayesian Network Model for Automated Speech Recognition – 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 […]

A novel deep learning approach to inferring postoperative outcome from imaging images – We conduct an overview of endoscopic MRI in real-world scenarios where the MR image is not available. The purpose of this paper is to review a few existing published works in endoscopic MRI. We hope they will help guide future research and […]

Learning Deep Transform Architectures using Label Class Discriminant Analysis – We propose and analyze a framework for automatic segmentation of high-resolution face images by exploiting the temporal and spatial information. Our novel framework is formulated as an extension of the K-SVD method and its predecessors. It consists of a Convolutional Neural Network (CNN), a Convolutional […]

On the importance of color reproduction in color reproduction in digital imaging – In particular, we provide a comparative analysis of various approaches to color reproduction through their different application to the control of color in computer vision. We provide three main contributions to this comparative study: (1) we show that the most commonly proposed […]

Stereoscopic Video Object Parsing by Multi-modal Transfer Learning – We propose a new class of 3D motion models for action recognition and video object retrieval based on visualizing objects in low-resolution images. Such 3D motion models are capable of capturing different aspects of the scene, such as pose, scale and lighting. These two aspects are […]

The Sigmoid Angle for Generating Similarities and Diversity Across Similar Societies – We develop a model-driven approach for a supervised machine translation system based on two-stage learning for both high-level and low-level language models. First, the system learns a mixture of high-level language models and then constructs a high-level language model based on the mixture […]