Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition
Handwritten mathematical expression recognition is a challenging problem due to the complicated two-dimensional structures, ambiguous handwriting input and variant scales of handwritten math symbols. This paper discusses the attention based encoder-decoder model that recognizes mathematical expression images from two-dimensional layouts to one-dimensional LaTeX strings. The […]
DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning
This paper presents a micro-traffic simulation (named “DeepTraffic”) where the perception, control, and planning systems for one of the cars are all handled by a single neural network as part of a model-free, off-policy reinforcement learning process. The paper also investigates the crowd-sourced hyperparameter tuning […]
Bitcoin: A Peer-to-Peer Electronic Cash System
The paper that started the Blockchain (and Bitcoin) revolution – Satoshi Nakamoto’s original whitepaper lays out the concept in simple, concise terms. A must read for anyone trying to understand the phenomenon.
Stable and Efficient Structures for the Content Production and Consumption in Information Communities
Real-world information communities exhibit inherent structures that characterize a system that is stable and efficient for content production and consumption. This paper studies such structures through mathematical modeling and analysis by formulating a generic model of a community in which each member decides how they […]
Will This Video Go Viral? Explaining and Predicting the Popularity of Youtube Videos
What makes content go viral? Which videos become popular and why others don’t? A range of models have been recently proposed to explain and predict popularity; however, there is a short supply of practical tools, accessible for regular users, that leverage these theoretical results. This […]
Novel Methods for Enhancing the Performance of Genetic Algorithms
This paper discusses the best approaches to take with Genetic algorithms (GA), a branch of evolutionary computing (EC) that mimics the theory of evolution and natural selection, where the technique is based on an heuristic random search. Crossover and mutation are the key to success […]
Detecting Offensive Language in Tweets Using Deep Learning
This paper addresses the important problem of discerning hateful content in social media. It proposes a detection scheme that is an ensemble of Recurrent Neural Network (RNN) classifiers, and it incorporates various features associated with user-related information, such as the users’ tendency towards racism or […]
Distributed Deep Reinforcement Learning: learn how to play Atari games in 21 minutes
This paper presents a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage ActorCritic (BA3C). Using synchronous training on the node level (while keeping the local, single node part of the algorithm […]