Mindblown: a blog about philosophy.

  • Sparse Multiple Instance Learning

    Sparse Multiple Instance Learning – Recent advances in the field of sparse multi-instance learning have produced numerous new data for analysis in high-dimensional data, and in the context of many other applications, such as image segmentation and sparse coding. However, there is relatively little research on multi-instance data and is therefore a challenge in the […]

  • Learning Visual Representations with Convolutional Neural Networks and Binary Networks for Video Classification

    Learning Visual Representations with Convolutional Neural Networks and Binary Networks for Video Classification – We present a simple system that aims to extract images from a video and predict what they will look like from that. We provide a simple algorithm based on a convolutional neural network to automatically learn the pose of the videos […]

  • Proceedings of the 2016 ICML Workshop on Human Interpretability in Artificial Intelligence

    Proceedings of the 2016 ICML Workshop on Human Interpretability in Artificial Intelligence – This paper presents a tool called BISNAP. It is a software package that supports the detection of objects with semantic and spatial information. In this paper, a set of data of a person and its objects are extracted with semantic information, and […]

  • Learning and reasoning about spatiotemporal temporal relations and hyperspectral data

    Learning and reasoning about spatiotemporal temporal relations and hyperspectral data – This paper presents a new model-based approach to understanding spatial and temporal information from an image, which provides a natural and simple representation for an image. First, an image is mapped to a set of its coordinate systems, which are then spatiotemporally represented as […]

  • Falling Fruit Eaters Over Higher-Order Tensor Networks

    Falling Fruit Eaters Over Higher-Order Tensor Networks – There are a number of existing methods that show that a particular number of data points is needed before a certain number of epochs to make a prediction. However, these methods do not consider temporal relations. A significant drawback of these methods is that the number of […]

  • Learning to Race by Sipping a Dr Pepper

    Learning to Race by Sipping a Dr Pepper – Many recent advances in data collection, analytics and machine learning techniques rely on machine learning methods, which can be used to construct rich models for data. Many machine learning approaches try to incorporate a high-level representation into the data using a graphical model, but it is […]

  • Fuzzy Classification of Human Activity with the Cyborg Astrobiologist on the Web

    Fuzzy Classification of Human Activity with the Cyborg Astrobiologist on the Web – In this paper, we proposed a method for a multi-tasking framework for real time task-based real-time image classification and summarization. The method proposes an efficient implementation using an iterative algorithm which uses the classification results to learn the underlying machine learning model […]

  • Stochastic Gradient Boosting

    Stochastic Gradient Boosting – This paper is the first to show that the model-based algorithm for a novel deep learning-based stochastic gradient rescaling algorithm can be easily derived from gradient-based stochastic gradient boosting. Our approach is fast and efficient, and we demonstrate its effectiveness on simulated data. The number of variables in a model is […]

  • Robust Online Sparse Subspace Clustering

    Robust Online Sparse Subspace Clustering – In this work, we propose a novel classifier for sparse sparse subspace clustering. We first show how to use the prior knowledge from sparse matrix classification to select the most relevant subspace samples. Next, we propose an online sparse subspace clustering technique that learns a sparse sparse subspace by […]

  • Learning to Transduch from GIFs to OCR

    Learning to Transduch from GIFs to OCR – This work develops a method for learning semantic image sequences through learning the semantic representation of a set of videos. The goal of this method is to learn semantic representations of videos by using video embeddings. In this paper, we show how such embeddings can be used […]

Got any book recommendations?