ΑΙhub.org
articles
Working towards explainable and data-efficient machine learning models via symbolic reasoning
Machine Learning Center at Georgia Tech
20 May 2020
By Yuan Yang
In recent years, we have witnessed the success of modern machine learning (ML) models. Many of them have led to unprecedented breakthroughs in a wide range of applications, such as Alp...
Shortcuts to artificial intelligence – a tale
Nello Cristianini
19 May 2020
The current paradigm of artificial intelligence emerged as the result of a series of cultural innovations, some technical and some social. Among them are seemingly small design decisions, that led to ...
Summarising the keynotes at ICLR: part one
Lucy Smith
14 May 2020
The virtual International Conference on Learning Representations (ICLR) was held on 26-30 April and included eight keynote talks, with a wide range of topics covered. In this post we summarise the fi...
Deep learning-guided surface characterization for autonomous fabrication
Jeremiah Croshaw
13 May 2020
The semiconductor industry as we know it is facing a critical roadblock that will lead to the end of Moore’s law. As transistors continue to shrink, quantum effects have a significant negative cons...
Unsupervised meta-learning: learning to learn without supervision
In unsupervised meta-learning, the agent proposes its own tasks, rather than relying on tasks proposed by a human.
By Benjamin Eysenbach (Carnegie Mellon University) and Abhishek Gupta (UC Berkeley...
Voice assistants – strategies for handling private information
COMPRISE
11 May 2020
In the latest in this series of posts, researchers from the EU-funded COMPRISE project write about privacy issues associated with voice assistants. They propose possible ways to maintain the privacy o...
Does on-policy data collection fix errors in off-policy reinforcement learning?
BAIR blog
06 May 2020
[latexpage]
By Aviral Kumar and Abhishek Gupta
Reinforcement learning has seen a great deal of success in solving complex decision making problems ranging from robotics to games to supply chai...
Hot papers on arXiv from the past month – April 2020
Lucy Smith
05 May 2020
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during April 2020.
Results are powered by Arxiv Sanity Preserver....
Learning DAGs with continuous optimization
ML@CMU
27 Apr 2020
Can we build a bridge between the left and right hand side?
[latexpage]
By Xun Zheng, Bryon Aragam and Chen Dan
As datasets continually increase in size and complexity, our ability to uncove...
BADGR: the Berkeley autonomous driving ground robot
BAIR blog
20 Apr 2020
By Greg Kahn
Look at the images above. If I asked you to bring me a picnic blanket in the grassy field, would you be able to? Of course. If I asked you to bring over a cart full of food for a party...
Machine learning tool may help us better understand RNA viruses
Machine Learning Center at Georgia Tech
15 Apr 2020
E2Efold is an end-to-end deep learning model developed at Georgia Tech that can predict RNA secondary structures, an important task used in virus analysis, drug design, and other public health applica...
Digital health interventions: predicting individual success using machine learning
University of Basel
13 Apr 2020
Health apps could be better tailored to the individual needs of patients. A statistical technique from the field of machine learning is now making it possible to predict the success of smartphone-base...
Explaining machine learning models for natural language
Machine Learning Center at Georgia Tech
10 Apr 2020
By Sarah Wiegreffe and Yuval Pinter
Natural language processing (NLP) is the study of how computers learn to represent and make decisions about human communication in the form of written text. This...
Speeding up transformer training and inference by increasing model size
BAIR blog
09 Apr 2020
By Eric Wallace
Model Training Can Be Slow
In deep learning, using more compute (e.g., increasing model size, dataset size, or training steps) often leads to higher accuracy. This is...
Machine learning to scale up the quantum computer
Muhammad Usman and Lloyd Hollenberg
08 Apr 2020
By Dr Muhammad Usman and Professor Lloyd Hollenberg
Quantum computers are expected to offer tremendous computational power for complex problems – currently intractable even on supercomputers ...
AlphaZero learns to solve quantum problems
By Mogens Dalgaard, Felix Motzoi, and Jacob Sherson
Technologies based on quantum physics, such as the quantum computer, have the potential to revolutionize our society. However, realizing these te...
Hot papers on arXiv from the past month – March 2020
Lucy Smith
01 Apr 2020
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during March 2020.
Results are powered by Arxiv Sanity Preserver....
Architecting a privacy-preserving dialogue system software development kit
COMPRISE
31 Mar 2020
By Gerrit Klasen
Use of dialogue systems such as Alexa, Siri, and Google Assistant raises several questions. In recent years, these virtual personal assistants have become the most popular represen...
AI scientific policies in China
Idees Magazine
30 Mar 2020
By Yi Chang and Chengqi Zhang
Artificial intelligence (AI) has entered into a new era, and its rapid development will profoundly affect the everyday life of citizens worldwide. Countries around the...
Are sixteen heads really better than one?
ML@CMU
26 Mar 2020
Hercules Slaying the Hydra
[latexpage]
By Paul Michel
Since their inception in this 2017 paper by Vaswani et al., transformer models have become a staple of NLP research. They are used in m...
Large-scale training at BAIR with Ray Tune
BAIR blog
25 Mar 2020
[latexpage]
By Richard Liaw, Eric Liang and Kristian Hartikainen
In this blog post, we share our experiences in developing two critical software libraries that many BAIR researchers ...
Can machines read our minds?
Nello Cristianini
20 Mar 2020
Many of us spend a significant portion of our day online and, in doing so, through our interactions with social media and IoT devices, leave a trail of “digital footprints” in our wake. Could this...
Combining AI and human expertise for cancer diagnosis
University of Waterloo
19 Mar 2020
Hamid Tizhoosh in his lab at the University of Waterloo. Image: University of Waterloo.
A new system combining artificial intelligence (AI) with human knowledge promises faster and more accurate ca...
Researchers use artificial intelligence to design supercompressible metamaterial
Miguel Bessa
18 Mar 2020
Researchers at TU Delft have developed a new material using Bayesian machine learning algorithms. Using the results of their computational simulations they have fabricated two designs at different len...
Working towards the next generation of voice interaction interfaces
COMPRISE
16 Mar 2020
COMPRISE (cost-effective, multilingual, privacy-driven voice-enabled services) is a European-funded Horizon 2020 project looking into the next generation of voice interaction services. The project ai...
Driverless shuttles: the latest from two European projects
Horizon
10 Mar 2020
Autonomous vehicles must be well-integrated into public transport systems if they are to take off in Europe's cities, say researchers. Image credit - Keolis
By Julianna Photopoulos
Jutting out i...
Emergent behavior by minimizing chaos
BAIR blog
09 Mar 2020
[latexpage]
By Glen Berseth
All living organisms carve out environmental niches within which they can maintain relative predictability amidst the ever-increasing entropy around the...
Predicting the coronavirus outbreak: how AI connects the dots to warn about disease threats
The Conversation
05 Mar 2020
Connecting the dots.
majcot/Shutterstock.com
By Vandana Janeja, University of Maryland, Baltimore County
Canadian artificial intelligence firm BlueDot has been in the news i...
Hot papers on arXiv from the past month – February 2020
Lucy Smith
02 Mar 2020
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during February 2020.
Results are powered by Arxiv Sanity Preserver....
Using deep learning to find disease-related genes
Linköping University
27 Feb 2020
Photo credit: metamorworks.
By Karin Söderlund Leifler
An artificial neural network can reveal patterns in huge amounts of gene expression data, and discover groups of disease-related genes. Th...
Deep learning AI discovers surprising new antibiotics
The Conversation
24 Feb 2020
A colored electron microscope image of MRSA.
NIH - NIAID/flickr, CC BY
By Sriram Chandrasekaran, University of Michigan
Imagine you’re a fossil hunter. You spend months in...
Fairness in artificial intelligence
Nello Cristianini
20 Feb 2020
Training machines using unbiased data and methodology is something that should be considered when designing artificial intelligence (AI) systems. Machine decisions can affect our rights, and we need ...
Neural approximate dynamic programming for on-demand ride-pooling
Sanket Shah
19 Feb 2020
In this post Sanket Shah (Singapore Management University) writes about his ride-pooling journey, from Bangalore to AAAI-20, with a few stops in-between....
What is my data worth?
BAIR blog
17 Feb 2020
[latexpage]
By Ruoxi Jia
People give massive amounts of their personal data to companies every day and these data are used to generate tremendous business values. Some economists and politicians...
How sensors and big data can help cut food wastage
The Conversation
05 Feb 2020
Shutterstock
By Jean Frederic Isingizwe Nturambirwe, Stellenbosch University and Umezuruike Linus Opara, Stellenbosch University
Modern farming has evolved by adopting technical advances such as...
Hot papers on arXiv from the past month – January 2020
Lucy Smith
04 Feb 2020
What’s hot on arXiv? Here are the most tweeted papers that were uploaded onto arXiv during January 2020.
Results are powered by Arxiv Sanity Preserver....
