ΑΙhub.org
articles
Benchmarking quality-diversity algorithms on neuroevolution for reinforcement learning
Manon Flageat and Bryan Lim
14 Dec 2022
We propose to apply QD to deep reinforcement learning tasks, and introduce a set of benchmarks to facilitate the comparison of approaches.
Causal confounds in sequential decision making
ML@CMU
06 Dec 2022
Using techniques from causal inference, we derive provably correct and scalable algorithms for sequential decision making in certain settings.
Estimating manipulation intentions to ease teleoperation
Anna Belardinelli
01 Dec 2022
Introducing an intention estimation model that relies on both gaze and motion features.
monthly digest
AIhub monthly digest: November 2022 – musical improvisation, two-player games, and interviews galore
Lucy Smith
29 Nov 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Collaboration the key to realising the potential of AI
Linköping University
28 Nov 2022
We are currently far from achieving full autonomy for rescue robotic systems. Consequently, well-functioning collaboration between human and machine is crucial.
Practical complexity of optimal play in games for two
Tomáš Peitl, Benjamin Böhm and Olaf Beyersdorff write about their IJCAI2022 award-winning paper on Quantified Conflict-Driven Clause Learning.
AI system for live music accompaniment and improvisation
Olga Vechtomova and Gaurav Sahu
23 Nov 2022
Musicians can perform together with LyricJam Sonic to explore connections between their live music and past recordings to generate new original compositions in real-time.
Studying AI recruitment tools: race, gender, and AI’s “eradication of difference”
University of Cambridge
11 Nov 2022
Claims AI can boost workplace diversity are ‘spurious and dangerous’, researchers argue.
Predicting properties of complex metamaterials
University of Amsterdam
08 Nov 2022
A research team tested how well machine learning can predict the properties of combinatorial mechanical metamaterials.
How shoring up drones with artificial intelligence helps surf lifesavers spot sharks at the beach
The Conversation
04 Nov 2022
Australian surf lifesavers are increasingly using drones to spot sharks at the beach before they get too close to swimmers. But just how reliable are they?
The White House’s “AI Bill of Rights” outlines five principles to make artificial intelligence safer, more transparent and less discrim
The Conversation
03 Nov 2022
Christopher Dancy takes a look at the five principles laid out in the USA AI Bill of Rights.
Using machine learning to improve all-in-one miniature spectrometers
University of Cambridge
31 Oct 2022
An international team of researchers have designed a miniaturised spectrometer that improves on current resolution records.
Machine learning predicts heat capacities of metal-organic frameworks
EPFL
28 Oct 2022
Chemical engineers have developed a machine-learning model that can accurately predict the heat capacity of the versatile metal-organic framework materials.
monthly digest
AIhub monthly digest: October 2022 – Nigerian sign language, a simple voting rule, and robotic control algorithms
Lucy Smith
27 Oct 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Accelerating laboratory automation through robot skill learning
Gabriella Pizzuto
26 Oct 2022
We introduce model-free reinforcement learning to the laboratory task of sample scraping.
The potential update on the protection of workers through the AI Act
Lola Montero and The Digital Constitutionalist
25 Oct 2022
A discussion of the significant legal scrutiny and numerous safeguards most workers’ data collection and processing activities would need to meet, as falling within the scope of high-risk AI systems.
Tackling diverse tasks with neural architecture search
ML@CMU
24 Oct 2022
We developed a Neural Architecture Search method that generates and trains task-specific convolutional neural networks.
New satellite mapping with AI can quickly pinpoint hurricane damage
The Conversation
20 Oct 2022
Using satellite images from before a storm and real-time images, together with machine learning, to create a disaster monitoring system that can map damage.
Trustworthy AI through regulation? Sketching the European approach
Can the European AI Act mitigate the ethical and legal concerns raised by AI technologies?
Tracking any pixel in a video
ML@CMU
17 Oct 2022
We propose Persistent Independent Particles (PIPs), a new particle video method to track pixels in a video.
Better understanding of cellular metabolism with the help of AI
EPFL
13 Oct 2022
EPFL scientists have released a deep-learning model for metabolic processes.
Applying explainable AI algorithms to healthcare
University of Amsterdam
11 Oct 2022
Ana Lucic has developed a framework for explaining predictions of machine learning models that could improve heart examinations for underserved communities.
Lizard in your luggage? We’re using artificial intelligence to detect wildlife trafficking
The Conversation
03 Oct 2022
Our research shows the potential for new technology to detect illegal wildlife in luggage or mail.
Keeping learning-based control safe by regulating distributional shift
BAIR blog
30 Sep 2022
We propose a new framework to reason about the safety of a learning-based controller with respect to its training distribution.
#IJCAI2022 distinguished paper – Plurality veto: A simple voting rule achieving optimal metric distortion
Fatih Erdem Kızılkaya
28 Sep 2022
How can we create a voting system that best represents the preferences of the voters?
monthly digest
AIhub monthly digest: September 2022 – environmental conservation, retrosynthesis, and RoboCup
Lucy Smith
27 Sep 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Recurrent model-free RL can be a strong baseline for many POMDPs
ML@CMU
23 Sep 2022
Considering an approach for dealing with realistic problems with noise and incomplete information.
State of the art in the RoboCup Humanoid League
Jasper Güldenstein and Marc Bestmann
22 Sep 2022
Summarising the different software and hardware components used by teams competing in the KidSize Humanoid League.
Algorithm learns to correct 3D printing errors for different parts, materials and systems
University of Cambridge
16 Sep 2022
Engineers from the University of Cambridge have developed a machine learning algorithm that can detect and correct a wide variety of different errors in real time.
Reverse engineering the NTK: towards first-principles architecture design
BAIR blog
12 Sep 2022
We propose a paradigm for bringing some principle to the art of architecture design.
Algorithmically finding ways to synthesize new medicine
Christopher Franz and Kevin Schewior
07 Sep 2022
Applying a well-known algorithm for solving two-player games to the problem of synthesizing new molecules.
Galaxies on graph neural networks
ML@CMU
05 Sep 2022
Using Graph Neural Networks, we trained Generative Adversarial Networks to correctly predict the coherent orientations of galaxies in a state-of-the-art cosmological simulation.
#IJCAI invited talk: engineering social and collaborative agents with Ana Paiva
Lucy Smith
02 Sep 2022
In her invited talk at IJCAI, Ana Paiva talked about some of her work on social robots and agents.
monthly digest
AIhub monthly digest: August 2022 – cross-lingual transfer, philosophy of cognitive science, and #DLIndaba
Lucy Smith
30 Aug 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
#IJCAI2022 invited talk: Insights in medicine with Mihaela van der Schaar
Lucy Smith
26 Aug 2022
Mihaela van der Schaar talks about some of the opportunities for machine learning in medicine.
auton-survival: An open-source package for regression, counterfactual estimation, evaluation and phenotyping censored time-to-event data
ML@CMU
22 Aug 2022
We present auton-survival – a comprehensive Python code repository of user-friendly, machine learning tools for working with censored time-to-event data.
