ΑΙhub.org
articles
Developing safe controllers for autonomous systems under uncertainty
Thom Badings and Nils Jansen
05 Apr 2022
Winners of a distinguished paper award at AAAI 2022, Thom S. Badings and Nils Jansen write about their work on robust control of autonomous systems.
Developing an AI-powered app to identify invasive bugs
CSIRO
04 Apr 2022
A team in Australia is using image recognition to help prevent stink bugs from entering the country.
Unsupervised skill discovery with contrastive intrinsic control
BAIR blog
01 Apr 2022
Unsupervised reinforcement learning (RL), where RL agents pre-train with self-supervised rewards, is an emerging paradigm for developing RL agents that are capable of generalization.
monthly digest
AIhub monthly digest: March 2022 – Lanfrica, AI index report, and conferences galore
Lucy Smith
29 Mar 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Deep learning: a framework for image analysis in life sciences
EPFL
25 Mar 2022
Researchers explore best practices for applying deep learning methods to bioimaging applications.
Assessing generalization of SGD via disagreement
ML@CMU
21 Mar 2022
We demonstrate that a simple procedure can accurately estimate the generalization error with only unlabeled data.
#AAAI2022 invited talks – data-centric AI and robust deep learning
Lucy Smith
16 Mar 2022
Hear from Andrew Ng and Marta Kwiatkowska, two of the plenary speakers at the AAAI Conference on Artificial Intelligence.
imodels: leveraging the unreasonable effectiveness of rules
BAIR blog
14 Mar 2022
imodels provides a simple unified interface and implementation for many state-of-the-art interpretable modeling techniques, particularly rule-based methods.
AI can help doctors work faster – but trust is crucial
Linköping University
11 Mar 2022
If artificial intelligence is to be of help in healthcare, people and machines must be able to work effectively together.
#AAAI2022 invited talk – Cynthia Rudin on interpretable machine learning
Lucy Smith
09 Mar 2022
The winner of the AAAI Squirrel AI award talks about using interpretable models for real-world applications, such as power grids and medicine.
Why spectral normalization stabilizes GANs: analysis and improvements
ML@CMU
07 Mar 2022
We investigate the training stability of generative adversarial networks (GANs).
Bart Selman’s presidential address at #AAAI2022 – incomprehensible truths, fragile chains and hidden crystals
Lucy Smith
03 Mar 2022
The current AAAI president talks about the state of AI and highlights three examples of AI for the acceleration of scientific discovery.
Hot papers on arXiv from the past month: February 2022
Lucy Smith
02 Mar 2022
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during February 2022.
monthly digest
AIhub monthly digest: February 2022 – AAAI 2022 in progress, the life of a dataset, and AI valentines
Lucy Smith
28 Feb 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Artificial intelligence and big data to help preserve wildlife
EPFL
25 Feb 2022
Research collaborators propose that animal ecologists can capitalize on large datasets generated by modern sensors by combining machine learning approaches with domain knowledge.
Beach bots, sea ‘raptors’ and marine toolsets mobilised to get rid of marine litter
Horizon
18 Feb 2022
Find out about the different EU research projects are concerned with reducing marine litter, including an autonomous litter-picking robot.
The unsupervised reinforcement learning benchmark
BAIR blog
14 Feb 2022
We consider the unsupervised RL problem - how do we learn useful behaviors without supervision and then adapt them to solve downstream tasks quickly?
Improving RL with lookahead: learning off-policy with online planning
ML@CMU
11 Feb 2022
We suggest using a policy that looks ahead using a learned model to find the best action sequence.
Machine learning fine-tunes graphene synthesis
Rice University
08 Feb 2022
Rice University lab uses computer models to advance graphene synthesis process.
Sequence modeling solutions for reinforcement learning problems
BAIR blog
03 Feb 2022
We tackle large-scale reinforcement learning problems with the toolbox of sequence modeling.
Hot papers on arXiv from the past month: January 2022
Lucy Smith
01 Feb 2022
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during January 2022.
monthly digest
AIhub monthly digest: January 2022 – new voices in AI, bug bounties, and arXiv hits two million
Lucy Smith
31 Jan 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Pulling back the curtain on neural networks
Oregon State University
28 Jan 2022
“Explainable AI is not something you produce or consume. It’s an educational experience, and the bottom line is that we need to focus on helping the humans to solve problems.”
#NeurIPS2021 invited talks round-up: part three – the collective intelligence of army ants
Lucy Smith
27 Jan 2022
In this third round-up of the invited talks at NeurIPS 2021, we cover the final talk by Radhika Nagpal.
AI powers autonomous materials discovery
Cornell University
25 Jan 2022
Integrating robotic materials synthesis and a hierarchy of AI methods to map out processing phase diagrams.
Artificial intelligence helps speed up ecological surveys
EPFL
24 Jan 2022
A deep-learning model for counting the number of seals in aerial photos that is considerably faster than doing it by hand.
An energy-based perspective on learning observation models
ML@CMU
21 Jan 2022
We propose a conceptually novel approach to mapping sensor readings into states.
RLiable: towards reliable evaluation and reporting in reinforcement learning
GoogleAI Blog
19 Jan 2022
Practical approaches to improve the rigour of deep reinforcement learning algorithm comparison.
#NeurIPS2021 invited talks round-up: part two – benign overfitting, optimal transport, and human and machine intelligence
Lucy Smith
14 Jan 2022
Continuing our series of round-ups of the invited talks from NeurIPS, we cover three more presentations.
Which mutual information representation learning objectives are sufficient for control?
BAIR blog
10 Jan 2022
How can we best design representation learning objectives?
Hot papers on arXiv from the past month: December 2021
Lucy Smith
06 Jan 2022
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during December 2021.
Keeping one step ahead of earthquakes
Horizon
04 Jan 2022
Damaging earthquakes can strike at any time. While we can’t prevent them from occurring, we can make sure casualties, economic loss and disruption of essential services are kept to a minimum.
Understanding user interfaces with screen parsing
ML@CMU
03 Jan 2022
We introduce the problem of screen parsing, which we use to predict structured user interface models from visual information.
Bridge data: boosting generalization of robotic skills with cross-domain datasets
BAIR blog
30 Dec 2021
With our proposed dataset and multi-task, multi-domain learning approach, we have shown one potential avenue for making diverse datasets reusable in robotics.
Artificial intelligence in 2021: the AIhub roundup
Lucy Smith
30 Dec 2021
As 2021 draws to a close we look back on some of the notable research developments, awards, news and policy in the world of artificial intelligence.
Hot papers on arXiv from 2021
Lucy Smith
27 Dec 2021
Find out which were the most-tweeted papers on arXiv from each month in 2021.
