ΑΙhub.org
articles
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.
Using reinforcement learning for control of direct ink writing
Institute of Science and Technology Austria
16 Aug 2022
Improving the printing technique of viscous materials using reinforcement learning and numerical simulation.
Why do policy gradient methods work so well in cooperative MARL? Evidence from policy representation
BAIR blog
15 Aug 2022
We show how policy gradient methods can converge to an optimal policy in certain cases, and that they can learn multi-modal policies.
Using AI to tackle the challenge of materials structure prediction
University of Cambridge
12 Aug 2022
Researchers have designed a machine learning method to predict the structure of new materials.
Using AlphaFold to find complex protein knots
Johannes Gutenberg Universität Mainz
11 Aug 2022
Theoretical physicists at Johannes Gutenberg University Mainz put AlphaFold to the test to find complex protein knots.
#ICML2022 invited talk round-up 2: estimating causal effects and drug discovery and development
Lucy Smith
10 Aug 2022
We summarise the final two invited talks from the International Conference on Machine Learning.
Art meets AI algorithms
Columbia University in the City of New York
05 Aug 2022
Find out about a collaboration between an artist and AI researchers.
#ICML2022 invited talk round-up 1: towards a mathematical theory of ML and using ML for molecular modelling
Lucy Smith
02 Aug 2022
We summarise the first two invited talks from the International Conference on Machine Learning.
Does AutoML work for diverse tasks?
ML@CMU
01 Aug 2022
Can the available AutoML tools quickly and painlessly attain near-expert performance on diverse learning tasks?
monthly digest
AIhub monthly digest: July 2022 – conferences galore, Lanfrica talks, and song contest winner announced
Lucy Smith
29 Jul 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
AI-powered BirdNET app makes citizen science easier
Cornell University
13 Jul 2022
The team behind BirdNET have published a paper about their work and what it means for citizen science.
FIGS: Attaining XGBoost-level performance with the interpretability and speed of CART
BAIR blog
12 Jul 2022
In this blog post we cover a new method for fitting an interpretable model that takes the form of a sum of trees.
Illustrating the materiality of AI
Better Images Of AI
01 Jul 2022
By picturing the physicality of artificial intelligence we hope to foster more accurate representations of these emerging technologies.
monthly digest
AIhub monthly digest: June 2022 – bootstrapped meta-learning, ethical AI, and a song contest
Lucy Smith
28 Jun 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
The Berkeley Crossword Solver
BAIR blog
27 Jun 2022
We recently built the Berkeley Crossword Solver (BCS), the first computer program to beat every human competitor in the world’s top crossword tournament.
