Advancing the collective intelligence of humans and machines through Deep Learning.

WHO WE ARE

Maluuba is a global leader in artificial intelligence research focused on teaching machines to think, reason and communicate.

Our vision is a world where intelligent machines work hand-in-hand with humans to advance the collective intelligence of the human species and bring about positive social and economic impacts.

We’re an early leader in using deep reinforcement learning to solve language-understanding problems and in training machines to model decision-making capabilities of the human brain.

OUR TECHNOLOGY

Our goal is to teach machines to understand human literacy.

MACHINE READING COMPREHENSION

READ. UNDERSTAND. REASON.

We are taking a unique approach to advancing the current state of Machine Reading Comprehension (MRC). By building systems that replicate how human beings learn to read, understand, and reason using state-of-the-art deep learning techniques, Maluuba is setting the standard for MRC technology.

CONVERSATIONAL USER INTERFACES

NATURAL CONVERSATIONS.

Maluuba’s work on Conversational User Interfaces focusses on building goal-driven dialogue bots that learn to engage in natural conversations with humans.

To achieve this, Maluuba has steered away from traditionally supervised techniques into novel reinforcement learning based techniques to optimize users’ satisfaction and agent’s knowledge acquisition simultaneously.

HOW IT WORKS

SEE HOW IT WORKS

MACHINE READING COMPREHENSION

QUERY UNDERSTANDING

The user query is represented as a sequence of semantic vectors, which are built into a working-memory representation.

PASSAGE UNDERSTANDING

A passage is read into episodic memory, again based on semantic vectors, and transformed into a hierarchical representation of words and sentences.

FOCUSSED ATTENTION

Comparisons are made between the query and passage representations; important chunks of the passage are summoned to working memory.

REASONING

The system reasons over salient episode chunks, which may interact with the question to modify its meaning. The reasoning module outputs an hypothesized answer.

Conversational User Interfaces

QUERY UNDERSTANDING 

The user query is represented as a sequence of semantic vectors, which are built into a working-memory representation.

STATE TRACKING

Contextual information from the dialogue, which is stored in episodic memory, is updated with the user’s query.

SEMANTIC KNOWLEDGE RETRIEVAL

Related knowledge stored in long-term memory is activated and combined with the state information.

DECISION MAKING & RESPONSE GENERATION

Based on the updated state, an optimal action is retrieved from procedural memory. The action is taken and an appropriate response is generated.

ADVISORS

DAVE GRANNAN

Mr. David L. Grannan, is a Co-founder of Light and serves as its Chief Executive Officer. Prior to Light, Dave was CEO of Vlingo, the first natural language speech recognition service for mobile phones. Vlingo provided speech recognition for the first Siri app and powered Samsung’s S-Voice product. Nuance Communications acquired Vlingo in 2012.

YOSHUA BENGIO

Yoshua Bengio is head of the Machine Learning Laboratory (MILA), CIFAR Program co-director of the CIFAR Neural Computation and Adaptive Perception program,  Canada Research Chair in Statistical Learning Algorithms, and he also holds the NSERC-Ubisoft industrial chair. His main research ambition is to understand principles of learning that yield intelligence. His research is widely cited (over 22000 citations found by Google Scholar in early 2015, with an H-index of 60).

RICHARD SUTTON

Richard S. Sutton is a fellow of the Association for the Advancement of Artificial Intelligence and co-author of the textbook Reinforcement Learning: An Introduction from MIT Press. Rich’s research interests centre on the learning problems facing a decision-maker interacting with its environment, which he sees as central to artificial intelligence.  He is also interested in animal learning psychology, in connectionist networks, and generally in systems that continually improve their representations and models of the world.

CAREERS

Work on cutting-edge research and help create applications that will change the world.
Maluuba is looking for exceptional individuals from a range of backgrounds to join our growing teams in Waterloo and Montreal.

PRESS