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
- Overview of Reinforcement Learning on December 21, 2018 at 3:52 pm
You might have heard of Google DeepMind beating several Atari games, beating a professional Go player, or even teaching a humanoid simulation to walk. This has been achieved with the help of ... […]
- Insilico to present on aging biomarkers at Longevity Therapeutics Summit 2019 in San Francisco on December 21, 2018 at 10:49 am
Artificial Intelligence (AI) techniques, such as deep learning (DL), reinforcement learning (RL), and generative adversarial networks (GANs) play a pivotal role in studying the biology of aging on man... […]
- Start your (machine learning) engines: Amazon’s DeepRacer is almost here on December 21, 2018 at 8:45 am
It's too bad we'll have to wait, because this car could help developers understand reinforcement learning, a type of machine learning commonly associated with self-driving cars, and it should ... […]
- Amazon Reveals Machine Learning Services on December 21, 2018 at 5:44 am
AWS introduced new Amazon SageMaker features making it easier for developers to build, train, and deploy machine learning models, features that include low cost, automatic data labeling, and reinforce... […]
- Insilico to present latest advances in deep learning for biomarker development at 2019 PMWC on December 20, 2018 at 7:59 am
Insilico pioneered the applications of the generative adversarial networks (GANs) and reinforcement learning for generation of novel molecular structures for the diseases with a known target and with ... […]
- The AI chip unicorn that's about to revolutionize everything has computational Graph at its Core on December 20, 2018 at 6:46 am
but it's also highly optimized for different machine learning approaches like reinforcement learning and future approaches too," he said. "The IPU architecture enables us to outperform GPUs -- it comb... […]
- What is neural architecture search? on December 20, 2018 at 4:08 am
Figure 2. Image courtesy of Determined AI. Interest in NAS ballooned after the work of Zoph, et. al., 2016 used reinforcement learning to design, at the time, state-of-the-art architectures for image ... […]
- Best of arXiv.org for AI, Machine Learning, and Deep Learning – November 2018 on December 19, 2018 at 3:49 pm
This paper discusses deep reinforcement learning in an overview style with six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contex... […]
- NVIDIA sets 6 AI performance records for deep learning workloads on December 17, 2018 at 5:05 am
the new "MLPerf" benchmark suite measures a wide range of deep learning workloads, covering areas as computer vision, language translation, personalised recommendations and reinforcement learning task... […]
via Bing News