Short Text Categorization using Deep Neural Networks and Word-Embedding Models

There are situations that we deal with short text, probably messy, without a lot of training data. In that case, we need external semantic information. Instead of using the conventional bag-of-words (BOW) model, we should employ word-embedding models, such as Word2Vec, GloVe etc. Suppose we want to perform supervised learning, with three subjects, described by … More Short Text Categorization using Deep Neural Networks and Word-Embedding Models

Linking Fundamental Physics to Deep Learning

Ever since Mehta and Schwab laid out the relationship between restricted Boltzmann machines (RBM) and deep learning mathematically (see my previous entry), scientists have been discussing why deep learning works so well. Recently, Henry Lin and Max Tegmark put a preprint on arXiv (arXiv:1609.09225), arguing that deep learning works because it captures a few essential … More Linking Fundamental Physics to Deep Learning

On Quantum Computing…

Justin Trudeau, the Canadian Prime Minister, rocked the world recently by talking about quantum computers in front of reporters at Perimeter Institute… No fault can be found in his answer, although his answer cannot be more layman. A few physicists were challenged to give a layman introduction about quantum computers, and they are equally well. … More On Quantum Computing…

Topology in Physics and Computing

Topology has been shown to reveal important information about geometry and shape from data, [Carlsson 2015][Carlsson 2009]¬†as I have talked about in various TDA blog entries. I have also demonstrated how to describe the topology if discrete data points by constructing simplicial complexes, and then calculated the homology and Betti numbers. (I will talk about … More Topology in Physics and Computing

Learning by Zooming Out

Deep learning, a collection of related neural network algorithms, has been proved successful in certain types of machine learning tasks in computer vision, speech recognition, data cleaning, and natural language processing (NLP). [Mikolov et. al. 2013] However, it was unclear how deep learning can be so successful. It looks like a black box with messy … More Learning by Zooming Out