ΑΙhub.org
articles
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.
Should I use offline RL or imitation learning?
BAIR blog
17 May 2022
In this blog post, we aim to understand if, when and why offline RL is a better approach for tackling a variety of sequential decision-making problems.
Using deep learning to predict physical interactions of protein complexes
Machine Learning Center at Georgia Tech
12 May 2022
A computational tool developed to predict the structure of protein complexes is providing new insights into the biomolecular mechanisms of their function.
#ICLR2022 invited talk round-up 2: Beyond interpretability
Lucy Smith
06 May 2022
In the second of our round-ups of the invited talks at ICLR we focus on the presentation by Been Kim.
Using machine-learning to distinguish antibody targets
University of Illinois
05 May 2022
Researchers have compiled an informative resource for antibody research and enhanced our molecular understanding of antibody responses.
Offline RL made easier: no TD learning, advantage reweighting, or transformers
BAIR blog
03 May 2022
We try to identify the essential elements of offline RL via supervised learning.
#ICLR2022 invited talk round-up 1: AI for science – protein structure prediction
Lucy Smith
29 Apr 2022
In this article, we summarise the ICLR invited talk given by Pushmeet Kohli.
monthly digest
AIhub monthly digest: April 2022 – images of AI, data justice, and winning at bridge
Lucy Smith
28 Apr 2022
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Trainee teachers made sharper assessments about learning difficulties after receiving feedback from AI
University of Cambridge
26 Apr 2022
Using AI to help trainee teachers in their assessments of students.
Using artificial intelligence in health sciences education requires interdisciplinary collaboration and risk assessment
The Conversation
19 Apr 2022
To better understand advances in AI as a part of the education of health sciences students, researchers conducted a comprehensive literature review and hosted a virtual panel.
Considering the risks of using AI to help grow our food
University of Cambridge
14 Apr 2022
Researchers warn that using new AI technologies at scale holds risks that are not being considered.
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.
