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
- Can Robots Learn to Set Their Own Goals? on February 21, 2019 at 12:57 pm
Specifically, the system matches each unknown task with the closest of the outcomes discovered during the intrinsic learning phase and then modifies this behavior using the reinforcement learning algo... […]
- Blue Danube Systems Enhances BeamPlanner™ Software Including Artificial Intelligence and Machine Learning Capabilities on February 21, 2019 at 12:01 pm
Reinforcement learning algorithms are implemented to enable a cycle of continuous improvement based on observations of and adaptation to live network conditions. Other AI/ML algorithms include pattern ... […]
- The evolution and expanding utility of Ray on February 21, 2019 at 9:14 am
Check out the RISE Lab tutorial "Building reinforcement learning models and AI applications with Ray" at the AI Conference in New York City, April 15-18, 2019. Early price ends March 1. How does this ... […]
- Best of arXiv.org for AI, Machine Learning, and Deep Learning – January 2019 on February 20, 2019 at 12:05 pm
They generally contain a high degree of mathematics so be prepared. Enjoy! Go-Explore: a New Approach for Hard-Exploration Problems A grand challenge in reinforcement learning is intelligent explorati... […]
- AI Startup Banks On Self-Learning Platform on February 20, 2019 at 11:24 am
Founded in 2015, Cogitai backed by Sony and is managed by a team of executives with extensive experience in AI and machine learning, including CEO Mark Ring, considered a pioneer in reinforcement lear... […]
- Most popular programming language frameworks and tools for machine learning on February 20, 2019 at 8:39 am
Described as a toolkit for developing and comparing algorithms for reinforcement-learning, a type of machine learning where software agents learn how to perform tasks by being rewarded for actions tha... […]
- New Study in Mice Reveals Unexpected Place for Learning, Memory in the Brain on February 20, 2019 at 7:49 am
This paper is titled "Reinforcement learning recruits somata and apical dendrites across layers of primary sensory cortex." Additional contributors include first author Clay Lacefield, PhD, Eftychios ... […]
- Edureka launches Machine Learning Engineer Master’s Program to meet rising demand for ML Engineers on February 18, 2019 at 10:48 pm
... latest advancements and technical approaches in Artificial Intelligence & Machine Learning such as Deep Learning, Graphical Models, Reinforcement Learning, Python Programming and Natural Language ... […]
- Cogitai 'Self-Learning' AI Platform Requires Less Training on February 18, 2019 at 2:48 pm
Cogitai is focused on the “second generation of AI” where AI can make decisions on its own based on a reinforcement learning. The Continua platform is now available for licensing, including a free, 60 ... […]
via Bing News