Research Demo on Children’s Stories and CNN News
Most of us read thousands of documents throughout our lives. Along with observation and communication, reading is one of the primary ways we learn. Almost all of human knowledge has been written down in some…
Game of Thrones: Marcy Demo
A demonstration of a deep learning bot (“Marcy”) answering reading comprehension questions about a plot summary of “Game of Thrones” plot summary.
Machine Reading Comprehension Demo
In this video we demonstrate how our technology can be used to read excerpts from books such as Harry Potter and more complex documents such as legal NDAs and medical journals.
Harry Potter & the Philosopher’s Stone Demo
Maluuba’s deep learning models reading excerpts from Harry Potter and answering questions based on comprehension.
Learning Optimal Interventions Under Uncertainty
A fundamental goal in data analysis is learning which actions (i.e. interventions) are optimal for producing a desired outcome within specific individuals or over an entire population. While advances in reinforcement learning, Bayesian optimization, and…
Efficient Second-order Optimization for Machine Learning
Stochastic gradient-based methods are the state-of-the-art in large-scale machine learning optimization due to their extremely efficient per-iteration computational cost. Second-order methods, that use the second derivative of the optimization objective, are known to enable faster…
From Deep Learning of Disentangled Representations to Higher-level Cognition
Abstract One of the main challenges for AI remains unsupervised learning, at which humans are much better than machines, and which we link to another challenge: bringing deep learning to higher-level cognition. We review earlier…