ΑΙhub.org
articles
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.
Deep attentive variational inference
ML@CMU
24 Jun 2022
The expressivity of current deep probabilistic models can be improved by selectively prioritizing statistical dependencies between latent variables that are potentially distant from each other.
AI and machine learning are improving weather forecasts, but they won’t replace human experts
The Conversation
20 Jun 2022
Machine learning can help with some of the challenges faced by weather forecasters.
Rethinking human-in-the-loop for artificial augmented intelligence
BAIR blog
17 Jun 2022
How do we build and evaluate an AI system for real-world applications?
Robotics people – #ICRA2022 Day 5 big wrap-up
David Garzón Ramos and Robohub
10 Jun 2022
The best part about participating in a robotics venue with nearly eight thousand attendees is, with no doubt, the robotics people.
Images Matter!
Merve Hickok and Better Images Of AI
08 Jun 2022
How we depict the state of technology (imagined, current or future) visually and verbally, helps us position ourselves in relation to what is already there and what is coming.
Designing societally beneficial reinforcement learning systems
BAIR blog
31 May 2022
Studying the risks associated with using reinforcement learning for real-world applications.
monthly digest
AIhub monthly digest: May 2022 – RoboCup virtual, neural collapse, and human-AI collaboration
Lucy Smith
30 May 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
The AI pretenders
Pursuit, University of Melbourne
27 May 2022
Researchers in Australia have investigated digital assistants and related privacy concerns of users.
New framework for cooperative bots aims to mimic high-performing human teams
Machine Learning Center at Georgia Tech
25 May 2022
Researchers have developed a robotics system for collaborative bots that work independently to achieve a shared goal.
Researching EU regulation around AI
University of Amsterdam
23 May 2022
A new research project will investigate regulation around AI, and how the EU approaches this issue.
An experimental design perspective on model-based reinforcement learning
ML@CMU
19 May 2022
We propose a simple algorithm that is able to solve a wide variety of control tasks.
Investigating neural collapse in deep classification networks
AIhub
18 May 2022
The winners of an outstanding paper award at ICLR 2022 tell us about their work on understanding deep neural networks.
