ΑΙhub.org
articles
An energy-based perspective on learning observation models
ML@CMU
21 Jan 2022
We propose a conceptually novel approach to mapping sensor readings into states.
RLiable: towards reliable evaluation and reporting in reinforcement learning
GoogleAI Blog
19 Jan 2022
Practical approaches to improve the rigour of deep reinforcement learning algorithm comparison.
#NeurIPS2021 invited talks round-up: part two – benign overfitting, optimal transport, and human and machine intelligence
Lucy Smith
14 Jan 2022
Continuing our series of round-ups of the invited talks from NeurIPS, we cover three more presentations.
Which mutual information representation learning objectives are sufficient for control?
BAIR blog
10 Jan 2022
How can we best design representation learning objectives?
Hot papers on arXiv from the past month: December 2021
Lucy Smith
06 Jan 2022
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during December 2021.
Keeping one step ahead of earthquakes
Horizon
04 Jan 2022
Damaging earthquakes can strike at any time. While we can’t prevent them from occurring, we can make sure casualties, economic loss and disruption of essential services are kept to a minimum.
Understanding user interfaces with screen parsing
ML@CMU
03 Jan 2022
We introduce the problem of screen parsing, which we use to predict structured user interface models from visual information.
Bridge data: boosting generalization of robotic skills with cross-domain datasets
BAIR blog
30 Dec 2021
With our proposed dataset and multi-task, multi-domain learning approach, we have shown one potential avenue for making diverse datasets reusable in robotics.
Artificial intelligence in 2021: the AIhub roundup
Lucy Smith
30 Dec 2021
As 2021 draws to a close we look back on some of the notable research developments, awards, news and policy in the world of artificial intelligence.
Hot papers on arXiv from 2021
Lucy Smith
27 Dec 2021
Find out which were the most-tweeted papers on arXiv from each month in 2021.
AI holidays 2021
AIhub
24 Dec 2021
Here's a sample of AI-themed holiday videos, images and stories to get you into the spirit this season.
Some highlights from our focus on the UN SDGs
Lucy Smith
22 Dec 2021
As 2021 draws to a close, we pick some of our favourite interviews and articles from our focus series on the UN sustainable development goals.
Why generalization in RL is difficult: epistemic POMDPs and implicit partial observability
BAIR blog
21 Dec 2021
In this blog post, we will aim to explain why generalization in RL is fundamentally hard, even in theory.
monthly digest
AIhub monthly digest: December 2021 – #NeurIPS2021, sustainable cities and the Reith lectures
Lucy Smith
20 Dec 2021
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Robot reinforcement learning: safety in real-world applications
How can we make a robot learn in the real world while ensuring safety? In this post, best paper award finalists at CoRL explain all.
Harnessing the power of AI to elucidate mobile traffic consumption at city scale
Paul Patras
15 Dec 2021
Mobile traffic analysis can provide many insights. Find out more about work on obtaining high-resolution traffic maps using AI methods and aggregate data.
Designs from data: offline black-box optimization via conservative training
BAIR blog
10 Dec 2021
In this post, we discuss offline model-based optimization and some recent advances in this area.
#NeurIPS2021 invited talks round-up: part one – Duolingo, the banality of scale and estimating the mean
Lucy Smith
09 Dec 2021
There are eight invited talks at the conference this year. In this post, we give a taster of the first three.
Smart cities and AI
Beril Sirmacek
03 Dec 2021
In this video lecture, Beril Sirmacek talks about research using AI methods to help to make cities more environmentally friendly.
Hot papers on arXiv from the past month: November 2021
Lucy Smith
01 Dec 2021
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during November 2021.
monthly digest
AIhub monthly digest: November 2021 – avoiding hype, musical dissonance, and AI thanksgiving
Lucy Smith
30 Nov 2021
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
A first-principles theory of neural network generalization
BAIR blog
22 Nov 2021
Find out more about research trying to shed light on the workings of deep neural networks.
Compression, transduction, and creation: a unified framework for evaluating natural language generation
ML@CMU
18 Nov 2021
Our framework classifies language generation tasks into compression, transduction, and creation.
Natural language processing model for African languages
University of Waterloo
17 Nov 2021
AfriBERTa model enables computers to analyse text in African languages for many useful tasks.
Machine learning for climate science and Earth observation – a webinar from Climate Change AI
Lucy Smith
16 Nov 2021
Hear from Maike Sonnewald and Gustau Camps-Valls, as they talk about trustworthy AI for climate analysis and physics-aware machine learning.
Making RL tractable by learning more informative reward functions: example-based control, meta-learning, and normalized maximum likelihood
BAIR blog
15 Nov 2021
This article presents MURAL, a method for learning uncertainty-aware rewards for RL.
Analysing ice hockey videos with deep learning
University of Waterloo
12 Nov 2021
Identifying players by their sweater numbers using multi-task learning.
PICO: Pragmatic compression for human-in-the-loop decision-making
BAIR blog
05 Nov 2021
In this post, we outline a pragmatic compression algorithm called PICO.
Hot papers on arXiv from the past month: October 2021
Lucy Smith
01 Nov 2021
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during October 2021.
Using imaging and machine learning tools to analyse features of plant leaves
University of Illinois
29 Oct 2021
Scientists have developed tools to discover attributes that contribute to water-use efficiency in crop plants during photosynthesis.
monthly digest
AIhub monthly digest: October 2021 – life on land, foundation models and Beethoven’s 10th
Lucy Smith
27 Oct 2021
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Unsolved ML safety problems
BAIR blog
26 Oct 2021
We provide a new roadmap for ML Safety and aim to refine the technical problems that the field needs to address.
What bird is singing? Merlin Bird ID app offers instant answers
Cornell University
19 Oct 2021
The Cornell Lab of Ornithology’s free Merlin Bird ID app can identify bird sounds.
Distilling neural networks into wavelet models using interpretations
BAIR blog
18 Oct 2021
We propose a method which distills information from a trained DNN into a wavelet transform.
Artificial intelligence can help highway departments find bats roosting under bridges
The Conversation
12 Oct 2021
Using photographs and computer vision techniques to automatically detect the presence of bats on bridges.
How a team of musicologists and computer scientists completed Beethoven’s unfinished 10th Symphony
The Conversation
08 Oct 2021
Find out more about the role of artificial intelligence in this project.
