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

WHO WE ARE

Our Machine Intelligence technology can be found in millions of smart devices, across various products and industries including Smart Phones, IoT ecosystems and other platforms.

Our vision is a world where intelligent machines work hand-in-hand with humans to advance the collective intelligence of the human species.

OUR TECHNOLOGY

We are building the world’s most advanced research facility in artificial intelligence with the goal of teaching machines to think, reason and communicate.

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.

SPOKEN DIALOGUE SYSTEMS

NATURAL CONVERSATIONS.

Maluuba’s research on Spoken Dialogue Systems (SDS) focusses on building goal-driven dialogue systems 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.

SPOKEN DIALOGUE SYSTEMS

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.

CAREERS

Maluuba is a fast-moving, work-hard-play-hard environment with a culture that supports collaboration, ideation, and encouragement.
We’re always on the look-out for new innovators to join our tribe.

PRESS