Group items tagged

AI week on BBC - interesting opportunity to get a glimpse into how the field is viewed by laymen...

From the section Science & Environment US researchers have developed what they call a "molten glass sewing machine" by combining 3D printing of glass with a mathematical model of how a liquid thread forms different types of loop. When the nozzle releasing a stream of molten glass is raised above a certain level, that thread begins to wobble.

In the past 12 months Americans have searched for Python on Google more often than for Kim Kardashian, a reality-TV star. The number of queries has trebled since 2010, while those for other major programming languages have been flat or declining.

Likely this is correlated with the increased interest in machine learning in the past decade - all the popular DL libraries are Python-based after all...

This is the future of publishing .... thinking to submit something there!! Anyone interested?

I tried reading the abstract and my eyes glazed over at the buzzword density. Is this hot doo doo or a meaningful result?

wow, quantum, artificial life, biomimetic, quantum supremacy .... quantum machine learning, and quantum artificial intelligence and, wait for it ...... quantum complexity. All in one abstract is this the new champion?

A good historical overview of the Deep Learning revolution. If you think the quote above is an exageration, here are some fresh news from Microsoft: Internal email: Microsoft forms new 5,000-person AI division

nice, did any of you try it already

Interesting paper on flexible pumps, maybe also of interest for thinner more comfortable EAV suits

"Hinton's new approach, known as capsule networks, is a twist on neural networks intended to make machines better able to understand the world through images or video. In one of the papers posted last week, Hinton's capsule networks matched the accuracy of the best previous techniques on a standard test of how well software can learn to recognize handwritten digits." Links to papers: https://arxiv.org/abs/1710.09829 https://openreview.net/forum?id=HJWLfGWRb&noteId=HJWLfGWRb

impressive!

seems a very impressive guy :"Hinton formed his intuition that vision systems need such an inbuilt sense of geometry in 1979, when he was trying to figure out how humans use mental imagery. He first laid out a preliminary design for capsule networks in 2011. The fuller picture released last week was long anticipated by researchers in the field. "Everyone has been waiting for it and looking for the next great leap from Geoff," says Kyunghyun Cho, a professor"

At SRI International in Silicon Valley, researchers have developed perhaps the most impressive microbot army yet: the MicroFactory. It's an ant colony made robotic, with half-millimeter machines zipping around to construct truly impressive structures.

This has been around for over a year. The current trend in deep learning is "deeper is better". But a consequence of this is that for a given network depth, we can only feasibly evaluate a tiny fraction of the "search space" of NN architectures. The current approach to choosing a network architecture is to iteratively add more layers/units and keeping the architecture which gives an increase in the accuracy on some held-out data set i.e. we have the following information: {NN, accuracy}. Clearly, this process can be automated by using the accuracy as a 'signal' to a learning algorithm. The novelty in this work is they use reinforcement learning with a recurrent neural network controller which is trained by a policy gradient - a gradient-based method. Previously, evolutionary algorithms would typically be used. In summary, yes, the results are impressive - BUT this was only possible because they had access to Google's resources. An evolutionary approach would probably end up with the same architecture - it would just take longer. This is part of a broader research area in deep learning called 'meta-learning' which seeks to automate all aspects of neural network training.

Btw that techxplore article was cringing to read - if interested read this article instead: https://research.googleblog.com/2017/05/using-machine-learning-to-explore.html

Using AI to design and build a micro organism to perform a task. Full publication can be found here: https://www.pnas.org/content/pnas/early/2020/01/07/1910837117.full.pdf

A very nice expo currently showcased in Berlin, well worth a visit. https://www.koeniggalerie.com/exhibitions/38455/machine-hallucinations-nature-dreams/ The concept is quite cool and teh result just stunning (I recommend giving the youtube videos a good luck on your TV if you have teh chance)

A somewhat eclectic paper about events collected with an event camera onboard the ISS, courtesy of Western Sydney University and...the US AirForce Academy.