Mindblown: a blog about philosophy.

Predicting Daily Activity with a Deep Neural Network – We present the first real-time and scalable approach for the problem of predicting the outcome of a simulated election. The prediction is performed during the course of a daily election. One particular feature of this challenge is that even for a few days, the forecast accuracy […]

The Role of Intensive Regression in Learning to Play StarCraft – In this paper we present a novel framework for predicting the importance of an actor’s performance in StarCraft games using a sequence of simple examples. This framework applies probabilistically, learning to a player’s state in a game, and to a character’s actions in the […]

High quality structured output learning using single-step gradient discriminant analysis – In this paper we propose a novel, efficient method for supervised prediction of large-scale image retrieval. Firstly, we first learn a novel dataset with a large domain of labels and an efficient classifier model to predict future examples. Then, we train the classifier model […]

A study to determine the maximum number of participants in the screening process for the Multi-Person Registration Platform – This article presents a methodology for the construction of a system for automated clinical examinations. Using a multidimensional feature extraction system, this paper proposes a strategy for the diagnosis and testing of cardiovascular diseases that is […]

Robust Learning of Spatial Context-Dependent Kernels – We investigate the use of latent variable models to train a machine-learned model to predict the location of objects. It is generally defined as a nonlinear network structure, and the network structure often consists of a fixed number of variables. In this paper, we model the network structure […]

Learning to Summarize a Sentence in English and Mandarin – We propose a Bayesian-based inference framework for the task of predicting the length of sentences. Our main component of the framework is an adaptive model of the sentence length. The model is used to build the graph of sentences that are predicted with respect to […]

Generating Semantic Representations using Greedy Methods – This paper presents an end-to-end approach for the semantic parsing of human language using machine learning based tools. The proposed approach is composed of two steps: (i) it learns semantic relationships by learning the representations learned by the human experts and (ii) it provides a natural way for […]

Scalable Algorithms for Learning Low-rank Mixtures with Large-Margin Classification – This paper presents a methodology for a hierarchical clustering model for classification tasks that use two or more classes. The class-specific clustering model is based in hierarchical clustering and can also be used to predict the clustering probability. The model can be used for all […]

On the Role of Context Dependency in the Performance of Convolutional Neural Networks in Task 1 Problems – In this work, we present an end-to-end convolutional neural network (CNN) that leverages the deep recurrent networks (RNNs) and their memory to perform tasks similar to those of the humans’ visual attention. While most CNNs have learned […]

Visual Tracking using Visual Tensor Factorization with Applications to Automated Vehicle Analysis and Tracking – We propose a new 3D-MAP method for semantic vehicle location based on spatial similarity map that aims to maximize the information gained by the 2D camera-based system. Based on the spatial similarity map, the system utilizes 3D point-based detection of […]