ΑΙhub.org
articles
A unifying, game-theoretic framework for imitation learning
ML@CMU
13 Aug 2021
In this post we explore imitation learning and consider online, offline, and interactive methods.
The surprising effectiveness of PPO in cooperative multi-agent games
BAIR blog
06 Aug 2021
A study of cooperative multi-agent tasks, in which a group of agents is trying to optimize a shared reward function.
Protecting user privacy with voice conversion
COMPRISE
04 Aug 2021
The COMPRISE project team discuss how to preserve privacy in automatic speech recognition systems.
Artificial intelligence speeds land-use classification
EPFL
03 Aug 2021
Method can distinguish complex land categories using infrared images and colour photos.
Hot papers on arXiv from the past month: July 2021
Lucy Smith
02 Aug 2021
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during July 2021.
monthly digest
AIhub monthly digest: July 2021 – ICML, protein folding for all, and AI Song Contest winner announced
Lucy Smith
29 Jul 2021
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Use of AI to fight COVID-19 risks harming “disadvantaged groups”, experts warn
University of Cambridge
28 Jul 2021
Rapid deployment of AI to tackle coronavirus must still go through ethical checks and balances.
#ICML2021 invited talk round-up 2: randomized controlled trials, encoding speech, and molecular science
Lucy Smith
27 Jul 2021
In our second round-up, we summarise the talks from Esther Duflo, Edward Chang and Cecilia Clementi.
Document grounded generation
ML@CMU
26 Jul 2021
A method for generating text when given a context and a source document.
#ICML2021 invited talk round-up 1: drug discovery and cryospheric science
Lucy Smith
21 Jul 2021
In this post, we summarise the first two invited talks from ICML, given by Daphne Koller and Xiao Cunde.
Ethics in voice technologies
COMPRISE
20 Jul 2021
This article from the COMPRISE project considers some of the ethical implications of voice technologies.
Ethics and AI: tackling biases hidden in big data
AIhub
16 Jul 2021
Find out more about Nello Cristianini's research into big data and biases.
What do pilots think of having more AI in the cockpit?
Pursuit, University of Melbourne
15 Jul 2021
Pilots are keen to explore using new technology in the cockpit but they also need to be central in the design of any new systems.
Code^Shift lab aims to confront bias in AI and machine learning
Texas A&M
13 Jul 2021
The new Texas A&M initiative brings together an interdisciplinary group of experts.
Four ways artificial intelligence is helping us learn about the universe
The Conversation
07 Jul 2021
Some of the biggest challenges in astronomy lie in how we’re going to study all the data we’re collecting.
The problem of complete, irreversible data anonymisation
COMPRISE
06 Jul 2021
Read about the challenges and the latest research into data anonymisation.
“I am here to assist you today” – how we respond to chatbots
University of Amsterdam
05 Jul 2021
Carolin Ischen studies how our perceptions of AI and our experience with chatbots influence our attitudes and behaviour.
Hot papers on arXiv from the past month: June 2021
Lucy Smith
02 Jul 2021
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during June 2021.
monthly digest
AIhub monthly digest: June 2021 – RoboCup, comics, and the return of the AI song contest
Lucy Smith
30 Jun 2021
Welcome to our monthly digest where you can catch up with AI research, events and news from the month past.
See, Hear, Explore: curiosity via audio-visual association
ML@CMU
29 Jun 2021
We propose a formulation of curiosity that encourages the agent to explore novel associations between modalities, such as audio and vision.
Cost-effective speech-to-text with weakly- and semi-supervised training
COMPRISE
28 Jun 2021
Find out how the COMPRISE project are using semi-supervised methods to train speech-to-text systems.
AI in port and maritime research
Universiteit Leiden
07 Jun 2021
Three researchers from The Netherlands explain their work.
FLeet: putting machine learning in your pocket
EPFL
02 Jun 2021
Using mobile devices to conduct machine learning as part of a distributed network.
monthly digest
AIhub monthly digest: May 2021 – ocean studies, defining AI, and philosophy of mind
Lucy Smith
28 May 2021
Welcome to our monthly digest where you can catch up with AI research, events and news from the month past.
Learning what to do by simulating the past
BAIR blog
24 May 2021
We propose an algorithm that can learn a policy without any human supervision or reward function.
A learning theoretic perspective on local explainability
ML@CMU
18 May 2021
By Vaishnavh Nagarajan and Jeffrey Li
[latexpage]
Fig 1: A formal relationship between interpretability and complexity. Going from left to right, we consider increasingly complex functions. As...
An active machine learning method for discovering new semiconductors
Technical University Of Munich
17 May 2021
Searching for new organic semiconductors, the basis for OLEDs and solar cells.
The importance of hyperparameter optimization for model-based reinforcement learning
BAIR blog
12 May 2021
We discuss how model-based reinforcement learning is more susceptible to parameter tuning and how we can use AutoML.
Artificial intelligence could be used to triage patients suspected at risk of early stage oesophageal cancer
University of Cambridge
10 May 2021
Find out how Cambridge researchers are using deep-learning to assist pathologists.
Counterfactual predictions under runtime confounding
ML@CMU
07 May 2021
We propose a method for using offline data to build a prediction model that only requires access to the available subset of confounders at prediction time.
Hot papers on arXiv from the past month: April 2021
Lucy Smith
05 May 2021
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during April 2021.
monthly digest
AIhub monthly digest: April 2021 – ethics, music, education and Westworld
Lucy Smith
04 May 2021
Welcome to our April 2021 monthly digest where you can catch up with any AIhub stories you may have missed, get the low-down on recent events, and much more.
Pretrained transformers as universal computation engines
BAIR blog
29 Apr 2021
Transformers have been successfully applied to a wide variety of modalities: natural language, vision, protein modeling, music, robotics, and more...
Studying biomolecules with deep-learning-enhanced nanoplasmonic technique
EPFL
27 Apr 2021
EPFL scientists have developed AI-enhanced nanosensors that let researchers track various kinds of biological molecules.
Quality education focus series round-up: teaching AI and using AI to improve teaching
Lucy Smith
26 Apr 2021
We summarise our focus series and highlight further interesting research in the field.
AAAI 2021 Spring Symposium on Implementing AI Ethics
Marija Slavkovik
23 Apr 2021
Marija Slavkovik takes a look at AI ethics and reports on the recent AAAI symposium.
