Feb 16, 2022 05:59 PM
(This post was last modified: Feb 16, 2022 06:13 PM by C C.)
The quest to make a digital replica of your brain
https://www.wired.co.uk/article/the-ques...your-brain
INTRO: Digital twins—virtual representations of real-world things—are already a mainstay in manufacturing, industry, and aerospace: There are digital doppelgängers of cities, ports, and power stations. The term was first introduced in 2010 by NASA researcher John Vickers in a report about the agency’s technology road maps, and industry analysts estimate the market for digital twins could reach nearly $50 billion by the year 2026.
It wasn’t long before the idea crept into biology. In 2016, Bill Ruh, then-CEO of GE Digital, predicted that “we will have a digital twin at birth, and it will take data off of the sensors everybody is running, and that digital twin will predict things for us about disease and cancer and other things.” A digital twin could inform tailored treatments for a patient and predict how their disease might develop. It could even be used to trial potential treatments, rather than testing them on the patient—a process that can be filled with risk.
So far, these projects are mostly in their early stages. A research program called Echoes, involving researchers in Europe, the United Kingdom, and the United States, is working to build a digital heart. Siemens Healthineers, a German medical device company, is aiming to do the same. Dassault Systèmes, a French software company, teamed up with the US Food and Drug Administration to approve what it calls “The Living Heart.” Austrian company Golem is creating digital twins of vulnerable people who live alone. The idea is that the digital twin continuously monitors their health, alerting caregivers if they fall ill and need help.
Now researchers are shooting for the loftiest goal: to twin the brain. Neurotwin, an EU-funded project, wants to design a computerized model of an individual patient’s entire brain. The Neurotwin team is hoping the model can be used to predict the effects of stimulation for the treatment of neurological disorders, including epilepsy and Alzheimer’s disease... (MORE - details)
DeepMind has trained an AI to control nuclear fusion
https://www.wired.co.uk/article/deepmind...ear-fusion
INTRO: The inside of a tokamak—the doughnut-shaped vessel designed to contain a nuclear fusion reaction—presents a special kind of chaos. Hydrogen atoms are smashed together at unfathomably high temperatures, creating a whirling, roiling plasma that’s hotter than the surface of the sun. Finding smart ways to control and confine that plasma will be key to unlocking the potential of nuclear fusion, which has been mooted as the clean energy source of the future for decades. At this point, the science underlying fusion seems sound, so what remains is an engineering challenge. “We need to be able to heat this matter up and hold it together for long enough for us to take energy out of it,” says Ambrogio Fasoli, director of the Swiss Plasma Center at École Polytechnique Fédérale de Lausanne in Switzerland.
That’s where DeepMind comes in. The artificial intelligence firm, backed by Google parent company Alphabet, has previously turned its hand to video games and protein folding, and has been working on a joint research project with the Swiss Plasma Center to develop an AI for controlling a nuclear fusion reaction.
In stars, which are also powered by fusion, the sheer gravitational mass is enough to pull hydrogen atoms together and overcome their opposing charges. On Earth, scientists instead use powerful magnetic coils to confine the nuclear fusion reaction, nudging it into the desired position and shaping it like a potter manipulating clay on a wheel. The coils have to be carefully controlled to prevent the plasma from touching the sides of the vessel: this can damage the walls and slow down the fusion reaction. (There’s little risk of an explosion as the fusion reaction cannot survive without magnetic confinement).
But every time researchers want to change the configuration of the plasma and try out different shapes that may yield more power or a cleaner plasma, it necessitates a huge amount of engineering and design work. Conventional systems are computer-controlled and based on models and careful simulations, but they are, Fasoli says, “complex and not always necessarily optimized.”
DeepMind has developed an AI that can control the plasma autonomously. A paper published in the journal Nature describes how researchers from the two groups taught a deep reinforcement learning system to control the 19 magnetic coils inside TCV, the variable-configuration tokamak at the Swiss Plasma Center, which is used to carry out research that will inform the design of bigger fusion reactors in the future. “AI, and specifically reinforcement learning, is particularly well suited to the complex problems presented by controlling plasma in a tokamak,” says Martin Riedmiller, control team lead at DeepMind... (MORE - details)
https://www.wired.co.uk/article/the-ques...your-brain
INTRO: Digital twins—virtual representations of real-world things—are already a mainstay in manufacturing, industry, and aerospace: There are digital doppelgängers of cities, ports, and power stations. The term was first introduced in 2010 by NASA researcher John Vickers in a report about the agency’s technology road maps, and industry analysts estimate the market for digital twins could reach nearly $50 billion by the year 2026.
It wasn’t long before the idea crept into biology. In 2016, Bill Ruh, then-CEO of GE Digital, predicted that “we will have a digital twin at birth, and it will take data off of the sensors everybody is running, and that digital twin will predict things for us about disease and cancer and other things.” A digital twin could inform tailored treatments for a patient and predict how their disease might develop. It could even be used to trial potential treatments, rather than testing them on the patient—a process that can be filled with risk.
So far, these projects are mostly in their early stages. A research program called Echoes, involving researchers in Europe, the United Kingdom, and the United States, is working to build a digital heart. Siemens Healthineers, a German medical device company, is aiming to do the same. Dassault Systèmes, a French software company, teamed up with the US Food and Drug Administration to approve what it calls “The Living Heart.” Austrian company Golem is creating digital twins of vulnerable people who live alone. The idea is that the digital twin continuously monitors their health, alerting caregivers if they fall ill and need help.
Now researchers are shooting for the loftiest goal: to twin the brain. Neurotwin, an EU-funded project, wants to design a computerized model of an individual patient’s entire brain. The Neurotwin team is hoping the model can be used to predict the effects of stimulation for the treatment of neurological disorders, including epilepsy and Alzheimer’s disease... (MORE - details)
DeepMind has trained an AI to control nuclear fusion
https://www.wired.co.uk/article/deepmind...ear-fusion
INTRO: The inside of a tokamak—the doughnut-shaped vessel designed to contain a nuclear fusion reaction—presents a special kind of chaos. Hydrogen atoms are smashed together at unfathomably high temperatures, creating a whirling, roiling plasma that’s hotter than the surface of the sun. Finding smart ways to control and confine that plasma will be key to unlocking the potential of nuclear fusion, which has been mooted as the clean energy source of the future for decades. At this point, the science underlying fusion seems sound, so what remains is an engineering challenge. “We need to be able to heat this matter up and hold it together for long enough for us to take energy out of it,” says Ambrogio Fasoli, director of the Swiss Plasma Center at École Polytechnique Fédérale de Lausanne in Switzerland.
That’s where DeepMind comes in. The artificial intelligence firm, backed by Google parent company Alphabet, has previously turned its hand to video games and protein folding, and has been working on a joint research project with the Swiss Plasma Center to develop an AI for controlling a nuclear fusion reaction.
In stars, which are also powered by fusion, the sheer gravitational mass is enough to pull hydrogen atoms together and overcome their opposing charges. On Earth, scientists instead use powerful magnetic coils to confine the nuclear fusion reaction, nudging it into the desired position and shaping it like a potter manipulating clay on a wheel. The coils have to be carefully controlled to prevent the plasma from touching the sides of the vessel: this can damage the walls and slow down the fusion reaction. (There’s little risk of an explosion as the fusion reaction cannot survive without magnetic confinement).
But every time researchers want to change the configuration of the plasma and try out different shapes that may yield more power or a cleaner plasma, it necessitates a huge amount of engineering and design work. Conventional systems are computer-controlled and based on models and careful simulations, but they are, Fasoli says, “complex and not always necessarily optimized.”
DeepMind has developed an AI that can control the plasma autonomously. A paper published in the journal Nature describes how researchers from the two groups taught a deep reinforcement learning system to control the 19 magnetic coils inside TCV, the variable-configuration tokamak at the Swiss Plasma Center, which is used to carry out research that will inform the design of bigger fusion reactors in the future. “AI, and specifically reinforcement learning, is particularly well suited to the complex problems presented by controlling plasma in a tokamak,” says Martin Riedmiller, control team lead at DeepMind... (MORE - details)