Homepage
Open in app
Sign inGet started

Lab Blog

We’ve moved! See our latest content on www.elementai.com/news !

Physical adversarial textures that fool visual object tracking

Physical adversarial textures that fool visual object tracking

While adversarial attacks have been proven effective in digital domains, few articles have shown the potency of such approaches in the…
Go to the profile of Rey Reza Wiyatno
Rey Reza Wiyatno
Sep 6, 2019
Modern recipes for anomaly detection

Modern recipes for anomaly detection

A quick tour of anomaly detection as I try to find Golden Retrievers in a celebrity faces dataset
Go to the profile of JC Testud
JC Testud
Mar 29, 2019
Securing machine learning models against adversarial attacks

Securing machine learning models against adversarial attacks

What are adversarial defences?
Go to the profile of Rey Reza Wiyatno
Rey Reza Wiyatno
Jan 9, 2019
Fast, careful adaptation with Bayesian MAML

Fast, careful adaptation with Bayesian MAML

Effective AI agents meant to work and learn in the real world should be quick to adapt to changes in their operational conditions. Where…
Go to the profile of Ousmane Dia
Ousmane Dia
Dec 3, 2018
Towards deep conversational recommendations

Towards deep conversational recommendations

Dialogue systems, or chatbots, are often divided in two categories: goal-oriented dialogue systems, and chit-chat dialogue systems…
Go to the profile of Raymond Li
Raymond Li
Nov 30, 2018
Improved few-shot learning for image classification

Improved few-shot learning for image classification

Few-shot Learning is the ability of an algorithm to learn a task by observing only a few samples. This is a popular tool in image…
Go to the profile of Pau Rodriguez
Pau Rodriguez
Nov 30, 2018
Join Element AI researchers at NeurIPS 2018!

Join Element AI researchers at NeurIPS 2018!

Come visit the dozens of Element AI researchers and employees at one of the biggest conferences in AI.
Go to the profile of Peter Henderson
Peter Henderson
Nov 30, 2018
A taxonomy of AI trustability challenges

A taxonomy of AI trustability challenges

In the first part of this series we established trustability as a key requirement for mass adoption and thus overall success of enterprise…
Go to the profile of Bahador Khaleghi
Bahador Khaleghi
Nov 8, 2018
The missing ingredient for mass adoption of AI: trust

The missing ingredient for mass adoption of AI: trust

AI is so hot right now. That’s confirmed by studies such as a recent Gartner report that calls AI an emerging “mega-trend.” In spite of…
Go to the profile of Bahador Khaleghi
Bahador Khaleghi
Nov 5, 2018
Insights on Montreal AI Symposium 2018

Insights on Montreal AI Symposium 2018

The Montreal AI Symposium was held at McGill University on August 28th, 2018. It gathered more than 600 participants, from the greater AI…
Go to the profile of EAI Science Curation
EAI Science Curation
Sep 28, 2018
About Element AI LabLatest StoriesArchiveAbout MediumTermsPrivacy