• about
  • resources
  • contribute
  • republishing guidelines
    • ☰
  • articles

    • articles

    Maximum entropy RL (provably) solves some robust RL problems

    Nearly all real-world applications of reinforcement learning involve some degree of shift between the training environment and the testing environment, and it is increasingly important to learn policies that are robust to these changes.
    14 April 2021, by

    Self-supervised policy adaptation during deployment

    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...
    09 April 2021, by

    Detection of marine litter using deep learning

    From left to right, the research team of Morgana Vighi, Odei García-Garin and Bertrand Bouchard. Photo credit: Àlex Aguilar (University of Barcelona - IRBio) Researchers at the University of Barc...
    07 April 2021, by

    Hot papers on arXiv from the past month: March 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....
    01 April 2021, by

    AIhub monthly digest: March 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.
    31 March 2021, by

    #NeurIPS2020 invited talks round-up: part three – causal learning and the genomic bottleneck

    In this post we conclude our summaries of the NeurIPS invited talks from the 2020 meeting. In this final instalment, we cover the talks by Marloes Maathuis (ETH Zurich) and Anthony M Zador (Cold Sprin...
    26 March 2021, by
    AIhub is supported by:
    reported elsewhere (by AITopics)
    ›   How Face Recognition Can Destroy Anonymity ›   A Fatal Crash Renews Concerns Over Tesla's 'Autopilot' Claim ›   Want to Get Along With Robots? Pretend They're Animals ›   Seeing Quadruple: Artificial Intelligence Leads to Discovery That Can Help Solve Cosmological Puzzles – SciTechDaily ›   Walmart Joins A Multibillion-Dollar Investment In Self-Driving Cars ›   Ocado in self-driving vans push with £10m stake in Oxbotica ›   Geoffrey Hinton has a hunch about what's next for AI ›   Robotic elephant trunk can learn new tasks on its own ›   Google is poisoning its reputation with AI researchers ›   Wrongfully arrested man sues Detroit police over false facial recognition match



    An inferential perspective on federated learning

    [latexpage] By Maruan Al-Shedivat TL;DR: motivated to better understand the fundamental tradeoffs in federated learning, we present a probabilistic perspective that generalizes and improves up...
    22 March 2021, by

    Michael Wooldridge: Talking to the public about AI – #EAAI2021 invited talk

    Photo by Kane Reinholdtsen on Unsplash Michael Wooldridge is the winner of the 2021 Educational Advances in Artificial Intelligence (EAAI) Outstanding Educator Award. He gave a plenary talk at AA...
    17 March 2021, by

    Climate action focus series round-up – interviews, research summaries, webinars and more

    In this summary article we highlight some of work at the intersection of AI and climate science.
    16 March 2021, by

    The successor representation, gamma-models, and infinite-horizon prediction

    [latexpage] Standard single-step models have a horizon of one. This post describes a method for training predictive dynamics models in continuous state spaces with an infinite, probabilistic horizon....
    12 March 2021, by

    Daphne Koller: Digital learning coming to life – #AAAI2021 invited talk

    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...
    11 March 2021, by

    Using machine learning to create texts for people with reading difficulties

    By David Isaksson The aim of the TextAD research project at Linköping University is to better understand different types of reading difficulties. This knowledge can be used to develop digital tool...
    10 March 2021, by

    Happy International Women’s Day!

    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...
    08 March 2021, by

    Team formation techniques in education

    Photo by Brooke Cagle on Unsplash Collaborative learning is gaining acceptance as one of the most successful educational approaches to learning. The basic idea is to organise learners in groups to ...
    04 March 2021, by

    AIhub monthly digest: February 2021

    [latexpage] Welcome to the second of our monthly digests, designed to keep you up-to-date with the happenings in the AI world. You can catch up with any AIhub stories you may have missed, get the low...
    03 March 2021, by

    Hot papers on arXiv from the past month – February 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....
    01 March 2021, by

    Machine learning helps retrace evolution of classical music

    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...
    26 February 2021, by

    How explainable artificial intelligence can help humans innovate

    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...
    23 February 2021, by

    Helping decision-makers manage resilience under different climate change scenarios: global vs local

    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...
    18 February 2021, by

    Does GPT-2 know your phone number?

    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...
    17 February 2021, by

    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...
    16 February 2021, by , , and

    Representational aspects of depth and conditioning in normalizing flows

    [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...
    15 February 2021, by

    Observing air quality and flow in cities for public health in times of climate change

    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...
    12 February 2021, by

    Good health and well-being: summarising AI and robotics in healthcare – diagnostics, personalised care, drug discovery, and more

    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 ...
    11 February 2021, by

    #AAAI2021 invited talk – Regina Barzilay on deploying machine learning methods in cancer diagnosis and drug design

    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...
    09 February 2021, by

    Offline reinforcement learning: how conservative algorithms can enable new applications

    [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...
    09 February 2021, by

    AI4Industry pilot releases first demonstration video

    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...
    08 February 2021, by

    AIhub monthly digest: January 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...
    04 February 2021, by

    Deep learning microscope for rapid tissue imaging

    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...
    04 February 2021, by

    Hot papers on arXiv from the past month – January 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....
    02 February 2021, by

     
    next page →



    ↑


  • news
  • articles
  • opinions
  • education


  • about
  • resources
  • contribute
  • republishing guidelines
  • RSS


  • linkedin
  • facebook
  • twitter
  • Youtube
















    • ©2021 - Association for the Understanding of Artificial Intelligence