Group items matching

in title, tags, annotations or url

Some work by DeepMind on applying reinforcement learning to teach a computer to navigate complex environments. Come for the science - stay for the video: https://goo.gl/8rTx2F

it works! No, of course it doesn't. I've wasted your time just posting this.

one of these again. french illustrations from 1910 of life in the year 2000. some pleasingly close. a lot of flying and robots. some inexplicable (bunch of people staring at a horse). some bmi.

No idea... another one I don't get is the one with the waiter presenting some small black-white thing to the white hair guy on a chair.

love the clockwork orange one

Loss of connectivity in the multisensory integration cortical areas after short term microgravity experience, which could explain astronauts decrease of performance in sensorimotor tasks and spatial working memory. However, the effect should wear off after a few days in microgravity and after adaptation to incongruent vestibular information. ISS experiment needed...

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

Research group is working on turning texts into executable code.

71 Arguments why the ACT needs legged robots and a pretty impressive work.

Let's keep a eye on this... Animals use odor cues to navigate through their environments, helping them locate targets and assess danger. Much of how animal brains organize, read out, and respond to odor stimuli across spatial and temporal scales is not well understood. To tackle these questions, Odor2Action uses a highly interdisciplinary team science approach. Our work uses fruit fly, honeybee, and mouse models to determine how neural representations of odor are generated, reformatted, and translated to generate useful behaviors that guide how animals interact with their environment.

reminds me of the methan smelling source finding study we did ...

Very cool recap document on state of the art sequential convex programming and lossless convexification techniques. It's written by the main authors who work on these, worth a look if you're into autonomous trajectory planning.

Now this looks quite convenient! :o

A nice look back into how JWST came to be and what it's all about. :)

About "Papers and patents are becoming less disruptive over time" https://www.nature.com/articles/s41586-022-05543-x. "Overall, our results deepen understanding of the evolution of knowledge and may guide career planning and science policy. To promote disruptive science and technology, scholars may be encouraged to read widely and given time to keep up with the rapidly expanding knowledge frontier. Universities may forgo the focus on quantity, and more strongly reward research quality56, and perhaps more fully subsidize year-long sabbaticals. Federal agencies may invest in the riskier and longer-term individual awards that support careers and not simply specific projects57, giving scholars the gift of time needed to step outside the fray, inoculate themselves from the publish or perish culture, and produce truly consequential work. Understanding the decline in disruptive science and technology more fully permits a much-needed rethinking of strategies for organizing the production of science and technology in the future."