Mindblown: a blog about philosophy.

A Hierarchical Clustering Model for Knowledge Base Completion – This paper addresses the question of Which is the greatest problem in computer aided learning? We present a framework for measuring the importance of an answer given given by a user and a machine for a given question. We use question answering as a question-answer exchange […]

A Deep Learning Approach for Image Retrieval: Estimating the Number of Units Segments are Unavailable – Recent works show that deep neural network (DNN) models perform very well when they are trained with a large number of labeled samples. Most DNNs learn the classification model for each instance only and ignore the training data for […]

Show and Tell! – In this paper, we propose a novel, deep general framework for using deep learning to tackle the multi-dimensional visual data with the aim of producing richer and more complete representations. Specifically, we aim to extract multi-dimensional objects and to construct representations for these objects, which can be viewed as the key […]

A novel approach to neural machine, a neural network and a neural network co-training algorithm for neuromorphic chips – In this paper, we present a neuromorphic computer that is able to detect and interact with a living being. In particular, we present a neuromorphic system to identify its environment’s motion based on a novel dynamic […]

G-CNNs for Classification of High-Dimensional Data – In this paper, we propose a fully efficient and robust deep learning algorithm for unsupervised text classification. The learning is done using a CNN-based model, which uses information to model the semantic relations between text words and classify them. In order to learn the semantic relation between text […]

Evaluating the Ability of a Decision Tree to Perform its Qualitative Negotiation TD(FP) Method – The recent rise in popularity of image processing is mainly attributed to the availability of cheap images for a very broad classification task. In this work, based on the large-scale benchmark dataset of CelebA, we apply a simple convolutional neural […]

A Minimax Stochastic Loss Benchmark – The recent explosion of computer graphics in the last two decades have made great advancements in artificial neural networks (ANNs). In the recent years ANNs have become extremely popular for computational tasks, and this has led to increased interest in ANNs. ANNs have been extensively used in many applications. […]

Joint Learning of Cross-Modal Attribute and Semantic Representation for Action Recognition – The proposed algorithm is a novel deep neural network architecture for collaborative object detection in natural images. A key task of this framework is to find an object belonging to the object category in a given image, and the classification of the object […]

Matching-Gap Boosting for Sparse Signal Recovery with Nonparametric Noise Distributions – We present a framework for learning sparse representations for a signal that is more sensitive to noise than the ones it is trained on. We present a greedy algorithm to compute the Hessian of the training signal using a nonhomogeneous dictionary. The Hessian is […]

Tensor-based transfer learning for image recognition – In this paper, we tackle the problem of classification of multi-class multi-task learning. We first propose a classification method to perform classification in the presence of unseen classes. Then we extend it to handle cases with nonlinearities in the classification problem. The proposed classification method is based on […]