articles


Learning state abstractions for long-horizon planning

[latexpage] By Scott Emmons*, Ajay Jain*, Michael Laskin*, Thanard Kurutach, Pieter Abbeel, Deepak Pathak Many tasks that we do on a regular basis, such as navigating a city, cooking a meal, or ...
29 January 2021, by

Using AI-enhanced music-supported therapy to assist stroke patients

Stroke currently ranks as the second most common cause of death and the second most common cause of disability worldwide. Motor deficits of the upper extremity (hemiparesis) are the most common and de...
26 January 2021, by

#NeurIPS2020 invited talks round-up: part two – the real AI revolution, and the future for the invisible workers in AI

In this post we continue our summaries of the NeurIPS invited talks from the 2020 meeting. Here, we cover the talks by Chris Bishop (Microsoft Research) and Saiph Savage (Carnegie Mellon University)....
22 January 2021, by

EvolveGraph: dynamic neural relational reasoning for interacting systems

[latexpage] By Jiachen Li Multi-agent interacting systems are prevalent in the world, from purely physical systems to complicated social dynamic systems. The interactions between entities / comp...
21 January 2021, by

High-performance computing and AI team up for COVID-19 diagnostic imaging

The Confederation of Laboratories for Artificial Intelligence Research in Europe (CLAIRE) taskforce on AI & COVID-19 supported the creation of a research group focused on AI-assisted diagnosis of COVI...
12 January 2021, by

Hot papers on arXiv from the past month – December 2020

What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during December 2020. Results are powered by Arxiv Sanity Preserver....
04 January 2021, by
AIhub is supported by:




CLAIRE COVID-19 taskforce webinar

By Joyce Anne Quinto As part of its second anniversary activities, CLAIRE hosted a webinar presenting the progress and future plans of its COVID-19 taskforce. Entitled, “CLAIRE taskforce for AI a...

Prediction of drug metabolites using deep learning

A computational tool created at Rice University may help pharmaceutical companies expand their ability to investigate the safety of drugs. (Credit: Kavraki Lab/Rice University) By Mike Williams ...
29 December 2020, by

Artificial intelligence in 2020: the AIhub roundup

As 2020 draws to a close we look back on some of the notable research developments, awards, conferences and policy in the world of artificial intelligence....
27 December 2020, by

Experiments with the ICML 2020 peer-review process

By Ivan Stelmakh The International Conference on Machine Learning (ICML) is a flagship machine learning conference that in 2020 received 4,990 submissions and managed a pool of 3,931 reviewers and ...
23 December 2020, by

The CLAIRE COVID-19 Initiative: a bottom-up effort from the European AI community

Figure 1: CLAIRE COVID-19 Initiative, topic groups and main outcomes By Gianluca Bontempi, Ricardo Chavarriaga, Hans de Canck, Emanuela Girardi, Holger Hoos and Iarla Kilbane-Dawe CLAIRE, the Co...

Opportunities for machine learning use in cystic fibrosis care

Blue and Brown Anatomical Lung Wall Decor. Credit: Hey Paul Studios. Accurately predicting how an individual’s chronic illness is going to progress is critical to delivering better-personalised, pr...
16 December 2020, by

Training on test inputs with amortized conditional normalized maximum likelihood

[latexpage] By Aurick Zhou Current machine learning methods provide unprecedented accuracy across a range of domains, from computer vision to natural language processing. However, in many impo...
14 December 2020, by

#NeurIPS2020 invited talks round-up: part one

There were seven interesting and varied invited talks at NeurIPS this year. Here, we summarise the first three, which were given by Charles Isbell (Georgia Tech), Jeff Shamma (King Abdullah University...
11 December 2020, by

AlphaFold advances protein folding research

Protein PCMT1 PDB, by Emw CC BY-SA 3.0, via Wikimedia Commons. The grand challenge of protein folding hit the news this week when it was announced that the latest version of DeepMind's AlphaFold sy...
03 December 2020, by

Hot papers on arXiv from the past month – November 2020

What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during November 2020. Results are powered by Arxiv Sanity Preserver....
01 December 2020, by

Goodhart’s law, diversity and a series of seemingly unrelated toy problems

[latexpage] By Aldo Pacchiano, Jack Parker-Holder, Luke Metz, and Jakob Foerster Goodhart’s Law is an adage which states the following: “When a measure becomes a target, it ceases to be a ...
30 November 2020, by

Adapting on the fly to test time distribution shift

By Marvin Zhang Imagine that you are building the next generation machine learning model for handwriting transcription. Based on previous iterations of your product, you have identified a key chall...
20 November 2020, by

Efficient graph construction to represent images

Why do we need graphs for image processing? Image processing over the years has evolved from simple linear averaging filters to highly adaptive non linear filtering operations such as the bilateral f...
12 November 2020, by

On learning language-invariant representations for universal machine translation

[latexpage] Figure 1: An encoder-decoder generative model of translation pairs, which helps to circumvent the limitation discussed before. There is a global distribution \(\mathcal{D}\) over the re...
09 November 2020, by

Reinforcement learning is supervised learning on optimized data

[latexpage] By Ben Eysenbach and Aviral Kumar and Abhishek Gupta The two most common perspectives on Reinforcement learning (RL) are optimization and dynamic programming. Methods that compute th...
05 November 2020, by

Hot papers on arXiv from the past month – October 2020

What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during October 2020. Results are powered by Arxiv Sanity Preserver....
02 November 2020, by

Improvising with an AI musician

For those interested in music and AI, a session on "Human collaboration with an AI musician" at the AI for Good global summit proved to be a real treat. The session included a performance between two ...
28 October 2020, by

Plan2Explore: active model-building for self-supervised visual reinforcement learning

By Oleh Rybkin, Danijar Hafner and Deepak Pathak [latexpage] To operate successfully in unstructured open-world environments, autonomous intelligent agents need to solve many different tasks and lea...
27 October 2020, by and

AWAC: accelerating online reinforcement learning with offline datasets

By Ashvin Nair and Abhishek Gupta [latexpage] Robots trained with reinforcement learning (RL) have the potential to be used across a huge variety of challenging real world problems. To apply RL...
19 October 2020, by

Generalizing randomized smoothing for pointwise-certified defenses to data poisoning attacks

We propose a method for making black-box functions provably robust to input manipulations. By training an ensemble of classifiers on randomly flipped training labels, we can use results from randomize...
16 October 2020, by

Five things to know about: making self-driving cars safe

By Jonathan O'Callaghan On 18 September, the European Commission published an independent expert report that looks at some of the outstanding safety and ethical issues around connected and automate...
12 October 2020, by

Hot papers on arXiv from the past month – September 2020

What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during September 2020. Results are powered by Arxiv Sanity Preserver....
07 October 2020, by

AI will change the world. Who will change AI? We will.

By Sophia Stiles [latexpage] Editor’s Note: The following blog is a special guest post by a recent graduate of Berkeley BAIR’s AI4ALL summer program for high school students. AI4ALL is a nonp...
05 October 2020, by

Adversarial generation of extreme samples

Modelling extreme events in order to evaluate and mitigate their risk is a fundamental goal in many areas, including extreme weather events, financial crashes, and unexpectedly high demand for online ...
01 October 2020, by




















©2021 - Association for the Understanding of Artificial Intelligence