ΑΙhub.org
articles
Tilted empirical risk minimization
ML@CMU
21 Apr 2021
We describe our work in tilted empirical risk minimization, which provides a unified view on the deficiencies of empirical risk minimization.
Maximum entropy RL (provably) solves some robust RL problems
BAIR blog
14 Apr 2021
It is important to learn policies that are robust to changes in environments.
Self-supervised policy adaptation during deployment
BAIR blog
09 Apr 2021
Our method learns a task in a fixed, simulated environment and quickly adapts to new environments (e.g. the real world) solely from online interaction during deployment.
By Nicklas Hansen and Xiaol...
Detection of marine litter using deep learning
Lucy Smith
07 Apr 2021
Understanding the problem of plastics in the oceans.
Hot papers on arXiv from the past month: March 2021
Lucy Smith
01 Apr 2021
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during March 2021.
Results are powered by Arxiv Sanity Preserver....
monthly digest
AIhub monthly digest: March 2021
Lucy Smith
31 Mar 2021
Welcome to our March 2021 monthly digest where you can catch up with any AIhub stories you may have missed, get the low-down on recent conferences, and much more.
#NeurIPS2020 invited talks round-up: part three – causal learning and the genomic bottleneck
Lucy Smith
26 Mar 2021
We summarise the plenaries from Marloes Maathuis and Anthony M Zador.
An inferential perspective on federated learning
ML@CMU
22 Mar 2021
We present a probabilistic perspective that generalizes and improves upon federated optimization and enables a new class of efficient federated learning algorithms.
Michael Wooldridge: Talking to the public about AI – #EAAI2021 invited talk
Lucy Smith
17 Mar 2021
Michael shares lessons learnt from his science communication experiences.
Climate action focus series round-up – interviews, research summaries, webinars and more
Lucy Smith
16 Mar 2021
In this summary article we highlight some of work at the intersection of AI and climate science.
The successor representation, gamma-models, and infinite-horizon prediction
BAIR blog
12 Mar 2021
Reinforcement learning algorithms are frequently categorized by whether they predict future states at any point in their decision-making process...
Daphne Koller: Digital learning coming to life – #AAAI2021 invited talk
Lucy Smith
11 Mar 2021
At AAAI 2021, Daphne Koller gave a plenary talk about digital learning. In this presentation she discussed the different motivations for online learning, what we know about effective learning, digital...
Using machine learning to create texts for people with reading difficulties
Linköping University
10 Mar 2021
The aim of the TextAD research project at Linköping University is to better understand different types of reading difficulties.
Happy International Women’s Day!
AIhub
08 Mar 2021
To celebrate International Women's Day, we take a look back over the past year of AIhub content and highlight some of our favourite articles, interviews, podcasts and videos, by, or featuring, women i...
Team formation techniques in education
Carles Sierra
04 Mar 2021
Our research uses combinatorial optimisation techniques to study team formation.
monthly digest
AIhub monthly digest: February 2021
Lucy Smith
03 Mar 2021
Welcome to the second of our monthly digests, designed to keep you up-to-date with the happenings in the AI world.
Hot papers on arXiv from the past month – February 2021
Lucy Smith
01 Mar 2021
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during February 2021.
Results are powered by Arxiv Sanity Preserver....
Machine learning helps retrace evolution of classical music
EPFL
26 Feb 2021
Researchers in EPFL’s Digital and Cognitive Musicology Lab used an unsupervised machine learning model to "listen to" and categorize more than 13,000 pieces of Western classical music, revealing how...
How explainable artificial intelligence can help humans innovate
The Conversation
23 Feb 2021
Understanding how artificial intelligence algorithms solve problems like the Rubik’s Cube makes AI more useful.
By Forest Agostinelli
The field of artificial intelligence (AI) has created comp...
Helping decision-makers manage resilience under different climate change scenarios: global vs local
Àngela Nebot
18 Feb 2021
The Intergovernmental Panel on Climate Change (IPCC) fifth assessment report states that warming of the climate system is unequivocal and notes that each of the last three decades has been successivel...
Does GPT-2 know your phone number?
BAIR blog
17 Feb 2021
By Eric Wallace, Florian Tramèr, Matthew Jagielski, and Ariel Herbert-Voss
[latexpage]
Most likely not.
Yet, OpenAI’s GPT-2 language model does know how to reach a certain Peter W--- (name r...
Physics-constrained deep learning of building thermal dynamics
Energy-efficient buildings are one of the top priorities to sustainably address the global energy demands and reduction of CO2 emissions. Advanced control strategies for buildings have been identified...
Representational aspects of depth and conditioning in normalizing flows
ML@CMU
15 Feb 2021
[latexpage]
Top and Bottom Right: RealNVP [3] uses checkerboard and channel-wise partitioning schemes in order to factor out parameters and ensure that there aren’t redundant partitions from previo...
Observing air quality and flow in cities for public health in times of climate change
Beril Sirmacek
12 Feb 2021
Sentinel 5P satellite for monitoring urban heat islands and the air pollution. Image source: Sharing Earth Observational Resources.
With my co-authors Pablo Torres, Sergio Hoyas (both from Institut...
Good health and well-being: summarising AI and robotics in healthcare – diagnostics, personalised care, drug discovery, and more
Lucy Smith
11 Feb 2021
In December 2020 we announced the launch of our focus series AI for Good: UN sustainable development goals (SDGs). Each month we pick a different sustainable development goal (SDG) and highlight work ...
#AAAI2021 invited talk – Regina Barzilay on deploying machine learning methods in cancer diagnosis and drug design
Lucy Smith
09 Feb 2021
In September 2020, Regina Barzilay was announced as the winner of the inaugural AAAI Squirrel AI award. Regina was formally presented with the prize during an award ceremony at the AAAI2021 conference...
Offline reinforcement learning: how conservative algorithms can enable new applications
BAIR blog
09 Feb 2021
[latexpage]
By Aviral Kumar and Avi Singh
Deep reinforcement learning has made significant progress in the last few years, with success stories in robotic control, game playing and science probl...
AI4Industry pilot releases first demonstration video
AI4EU
08 Feb 2021
Screengrab from the demonstration video produced by AI4Industry
By AI4EU’s AI4Industry pilot team
AI4EU's pilot AI4Industry released its first video to demonstrate how AI techniques can help d...
monthly digest
AIhub monthly digest: January 2021
Lucy Smith
04 Feb 2021
We are introducing a monthly digest to keep you up-to-date with the latest happenings in the AI world. You can catch up with any AIhub stories you may have missed, get the low-down on recent conferenc...
Deep learning microscope for rapid tissue imaging
Rice University
04 Feb 2021
Rice University engineering researchers Yubo Tang (left) and Mary Jin are members of a team that used deep learning to optimize both image collection and image post-processing in a new type of microsc...
Hot papers on arXiv from the past month – January 2021
Lucy Smith
02 Feb 2021
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during January 2021.
Results are powered by Arxiv Sanity Preserver....
Learning state abstractions for long-horizon planning
BAIR blog
29 Jan 2021
[latexpage]
By Scott Emmons*, Ajay Jain*, Michael Laskin*, Thanard Kurutach, Pieter Abbeel, Deepak Pathak
Many tasks that we do on a regular basis, such as navigating a city, cooking a meal, or ...
Using AI-enhanced music-supported therapy to assist stroke patients
Josep Lluís Arcos
26 Jan 2021
Stroke currently ranks as the second most common cause of death and the second most common cause of disability worldwide. Motor deficits of the upper extremity (hemiparesis) are the most common and de...
#NeurIPS2020 invited talks round-up: part two – the real AI revolution, and the future for the invisible workers in AI
Lucy Smith
22 Jan 2021
In this post we continue our summaries of the NeurIPS invited talks from the 2020 meeting. Here, we cover the talks by Chris Bishop (Microsoft Research) and Saiph Savage (Carnegie Mellon University)....
EvolveGraph: dynamic neural relational reasoning for interacting systems
BAIR blog
21 Jan 2021
[latexpage]
By Jiachen Li
Multi-agent interacting systems are prevalent in the world, from purely physical systems to complicated social dynamic systems. The interactions between entities / comp...
High-performance computing and AI team up for COVID-19 diagnostic imaging
Marco Aldinucci
12 Jan 2021
The Confederation of Laboratories for Artificial Intelligence Research in Europe (CLAIRE) taskforce on AI & COVID-19 supported the creation of a research group focused on AI-assisted diagnosis of COVI...
