Reverse Engineering source code vaccine BioNTech / Pfizer SARS-CoV-2

Now, these words may be somewhat jarring – the vaccine is a liquid that gets injected in your arm. How can we talk about source code?

This is a good question, so let’s start off with a small part of the very source code of the BioNTech/Pfizer vaccine, also known as BNT162b2, also known as Tozinameran also known as Comirnaty.

 

First 500 characters of the BNT162b2 mRNA. Source: World Health Organization
First 500 characters of the BNT162b2 mRNA. Source: World Health Organization

The BNT162b2 mRNA vaccine has this digital code at its heart. It is 4284 characters long, so it would fit in a bunch of tweets. At the very beginning of the vaccine production process, someone uploaded this code to a DNA printer (yes), which then converted the bytes on disk to actual DNA molecules.

 

Full article: https://berthub.eu/articles/posts/reverse-engineering-source-code-of-the-biontech-pfizer-vaccine/

 

Machine Learning’s ‘Amazing’ Ability to Predict Chaos

In new computer experiments, artificial-intelligence algorithms can tell the future of chaotic systems.
Gif illustration for "Machine Learning’s ‘Amazing’ Ability to Predict Chaos"

Researchers have used machine learning to predict the chaotic evolution of a model flame front.

Half a century ago, the pioneers of chaos theory discovered that the “butterfly effect” makes long-term prediction impossible. Even the smallest perturbation to a complex system (like the weather, the economy or just about anything else) can touch off a concatenation of events that leads to a dramatically divergent future. Unable to pin down the state of these systems precisely enough to predict how they’ll play out, we live under a veil of uncertainty.

In a series of results reported in the journals Physical Review Letters and Chaos, scientists have used machine learning — the same computational technique behind recent successes in artificial intelligence — to predict the future evolution of chaotic systems out to stunningly distant horizons. The approach is being lauded by outside experts as groundbreaking and likely to find wide application.

“I find it really amazing how far into the future they predict” a system’s chaotic evolution, said Herbert Jaeger, a professor of computational science at Jacobs University in Bremen, Germany  …. <more>

Graphic illustration depicting the charts of training computers to predict chaos.

Full pages:

https://www.wired.com/story/machine-learnings-amazing-ability-to-predict-chaos/

https://www.quantamagazine.org/machine-learnings-amazing-ability-to-predict-chaos-20180418/

 

 

Microsoft researchers build a bot that draws what you tell it to

If you’re handed a note that asks you to draw a picture of a bird with a yellow body, black wings and a short beak, chances are you’ll start with a rough outline of a bird, then glance back at the note, see the yellow part and reach for a yellow pen to fill in the body, read the note again and reach for a black pen to draw the wings and, after a final check, shorten the beak and define it with a reflective glint. Then, for good measure, you might sketch a tree branch where the bird rests.

Now, there’s a bot that can do that, too.

The new artificial intelligence technology under development in Microsoft’s research labs is programmed to pay close attention to individual words when generating images from caption-like text descriptions. This deliberate focus produced a nearly three-fold boost in image quality compared to the previous state-of-the-art technique for text-to-image generation, according to results on an industry standard test reported in a research paper posted on arXiv.org.

The technology, which the researchers simply call the drawing bot, can generate images of everything from ordinary pastoral scenes, such as grazing livestock, to the absurd, such as a floating double-decker bus. Each image contains details that are absent from the text descriptions, indicating that this artificial intelligence contains an artificial imagination.

Continue reading: https://blogs.microsoft.com/ai/drawing-ai/

A deep-learning tool that lets you clone an artistic style onto a photo

The Deep Photo Style Transfer tool lets you add artistic style and other elements from a reference photo onto your photo. (credit: Cornell University)

“Deep Photo Style Transfer” is a cool new artificial-intelligence image-editing software tool that lets you transfer a style from another (“reference”) photo onto your own photo, as shown in the above examples.

An open-access arXiv paper by Cornell University computer scientists and Adobe collaborators explains that the tool can transpose the look of one photo (such as the time of day, weather, season, and artistic effects) onto your photo, making it reminiscent of a painting, but that is still photorealistic.

The algorithm also handles extreme mismatch of forms, such as transferring a fireball to a perfume bottle. (credit: Fujun Luan et al.)

“What motivated us is the idea that style could be imprinted on a photograph, but it is still intrinsically the same photo, said Cornell computer science professor Kavita Bala. “This turned out to be incredibly hard. The key insight finally was about preserving boundaries and edges while still transferring the style.”

To do that, the researchers created deep-learning software that can add a neural network layer that pays close attention to edges within the image, like the border between a tree and a lake.

The software is still in the research stage.

Bala, Cornell doctoral student Fujun Luan, and Adobe collaborators Sylvian Paris and Eli Shechtman will present their paper at the Conference on Computer Vision and Pattern Recognition on July 21–26 in Honolulu.

This research is supported by a Google Faculty Re-search Award and NSF awards.


Abstract of Deep Photo Style Transfer

This paper introduces a deep-learning approach to photographic style transfer that handles a large variety of image content while faithfully transferring the reference style. Our approach builds upon the recent work on painterly transfer that separates style from the content of an image by considering different layers of a neural network. However, as is, this approach is not suitable for photorealistic style transfer. Even when both the input and reference images are photographs, the output still exhibits distortions reminiscent of a painting. Our contribution is to constrain the transformation from the input to the output to be locally affine in colorspace, and to express this constraint as a custom fully differentiable energy term. We show that this approach successfully suppresses distortion and yields satisfying photorealistic style transfers in a broad variety of scenarios, including transfer of the time of day, weather, season, and artistic edits.