Is it a computer program or a living being? At TU Wien (Vienna), the boundaries become blurred. The neural system of a nematode was translated into computer code – and then the virtual worm was taught amazing tricks.
It is not much to look at: the nematode C. elegans is about one millimetre in length and is a very simple organism. But for science, it is extremely interesting. C. elegans is the only living being whose neural system has been analysed completely. It can be drawn as a circuit diagram or reproduced by computer software, so that the neural activity of the worm is simulated by a computer program.
Such an artificial C. elegans has now been trained at TU Wien (Vienna) to perform a remarkable trick: The computer worm has learned to balance a pole at the tip of its tail.
The Worm’s Reflexive behaviour as Computer Code
C. elegans has to get by with only 300 neurons. But they are enough to make sure that the worm can find its way, eat bacteria and react to certain external stimuli. It can, for example, react to a touch on its body. A reflexive response is triggered and the worm squirms away.
This behaviour can be perfectly explained: it is determined by the worm’s nerve cells and the strength of the connections between them. When this simple reflex-network is recreated on a computer, then the simulated worm reacts in exactly the same way to a virtual stimulation – not because anybody programmed it to do so, but because this kind of behaviour is hard-wired in its neural network.
“This reflexive response of such a neural circuit, is very similar to the reaction of a control agent balancing a pole”, says Ramin Hasani (Institute of Computer Engineering, TU Wien). This is a typical control problem which can be solved quite well by standard controllers: a pole is fixed on its lower end on a moving object, and it is supposed to stay in a vertical position. Whenever it starts tilting, the lower end has to move slightly to keep the pole from tipping over. Much like the worm has to change its direction whenever it is stimulated by a touch, the pole must be moved whenever it tilts.
Mathias Lechner, Radu Grosu and Ramin Hasani wanted to find out, whether the neural system of C. elegans, uploaded to a computer, could solve this problem – without adding any nerve cells, just by tuning the strength of the synaptic connections. This basic idea (tuning the connections between nerve cells) is also the characteristic feature of any natural learning process.
A Program without a Programmer
“With the help of reinforcement learning, a method also known as ‘learning based on experiment and reward’, the artificial reflex network was trained and optimized on the computer”, Mathias Lechner explains. And indeed, the team succeeded in teaching the virtual nerve system to balance a pole. “The result is a controller, which can solve a standard technology problem – stabilizing a pole, balanced on its tip. But no human being has written even one line of code for this controller, it just emerged by training a biological nerve system”, says Radu Grosu.
The team is going to explore the capabilities of such control-circuits further. The project raises the question, whether there is a fundamental difference between living nerve systems and computer code. Is machine learning and the activity of our brain the same on a fundamental level? At least we can be pretty sure that the simple nematode C. elegans does not care whether it lives as a worm in the ground or as a virtual worm on a computer hard drive.
The Latest on: Reinforcement learning
via Google News
The Latest on: Reinforcement learning
- Designing new drugs takes years, but A.I. could help reduce that to dayson September 7, 2019 at 7:09 am
In 2017, they combined this with another type of groundbreaking A.I. in the form of Reinforcement Learning. Reinforcement Learning, most famously used by Google DeepMind to produce a video game ...
- KBR Partners With AWS, NASA to Hold Autonomous Vehicle Racing Event; Byron Bright Quotedon September 6, 2019 at 8:57 am
KBR said Aug. 22 its interns and employees worked with NASA at Goddard Space Flight Center to test an ML technique called reinforcement learning during the AWS DeepRacer event. Reinforcement learning ...
- How machine learning helps important industrieson September 6, 2019 at 6:00 am
Supervised learning (Learning from previous examples) Reinforcement learning (Learning through a series of rewards and punishments) Only five decades ago, machine learning was considered science ...
- Ageing research to accelerate with experimental validation in AI-powered drug discoveryon September 4, 2019 at 2:33 pm
By using a combination of Generative Adversarial Networks (GANs) and Reinforcement Learning (RL), the team of Insilico Medicine researchers behind this study (documented in a paper published in Nature ...
- 5 Signs It's Time to Switch Your Business Bankon September 4, 2019 at 11:58 am
The e-commerce giant has announced an autonomous toy car which can be programmed to drive itself via a technique called reinforcement learning. George HW Bush Bush was a humble leader, who ...
- AI-powered drug discovery in days, not yearson September 4, 2019 at 12:08 am
This is an acronym for Generative Tensorial Reinforcement Learning) As described in the study, GENTRL was able to successfully identify six promising treatments for fibrosis in just 21 days, with one ...
- A breakthrough in imaginative AI with experimental validation to accelerate drug discoveryon September 3, 2019 at 2:25 pm
The many advances in deep learning reinforcement learning and generative adversarial learning made since 2014 are rapidly transforming multiple industries including search, translation, video games, ...
- Novel Molecules Designed by Artificial Intelligence in 21 Days Are Validated in Miceon September 3, 2019 at 11:24 am
The paper describes a timed challenge, where the new artificial intelligence system called Generative Tensorial Reinforcement Learning (GENTRL) designed six novel inhibitors of DDR1, a kinase target ...
- The Hedge Fund That Wasn’ton September 3, 2019 at 11:08 am
Thrones Capital strategy leverages artificial intelligence and big data analytics with supervise learning and reinforcement learning algorithms. The artificial intelligence engine learns historical ...
via Bing News