Google's DeepMind: dopamine use from neural networks

: Οι αλγόριθμοι βαθιάς μάθησης μπορούν να ξεπεράσουν την ανθρώπινη σε πολλά σημεία: από την ταξινόμηση εικόνων, μέχρι την ανάγνωση ομιλίας από τα χείλια, έως τις ακριβείς προβλέψεις για το μέλλον. Όμως παρά τα υπεράνθρωπα επίπεδα επάρκειας τους, μειονεκτούν στο ρυθμό με τον οποίο μαθαίνουν.

Some of the best mechanical learning algorithms need hundreds of hours to study and learn classic video games, something a man can learn in an afternoon. The fact may be somewhat related to neurotransmitter dopamine, according to a publication of Google's subsidiary DeepMind in Nature Neuroscience.DeepMind

Η μετα-μάθηση ή η γρήγορης εκμάθησης από παραδείγματα και η απόκτηση κανόνων από αυτά τα παραδείγματα με την πάροδο του χρόνου πιστεύεται ότι είναι ένας από τους τρόπους με τους οποίους οι άνθρωποι αποκτούν νέες γνώσεις αποτελεσματικότερα από τους αλγόριθμους. Όμως οι βασικοί μηχανισμοί της μετα-μάθησης είναι προς το παρόν ελάχιστα κατανοητοί.

In an effort to shed light on the process, DeepMind researchers in London modeled human physiology using a recurring neural network, a type of neural network that is capable of internalizing previous actions and observations and learning from these experiences. The system that mathematically optimizes the algorithm over time through tests and errors is reportedly using dopamine, a chemical in the brain that affects feelings, movements, sensations of pain and pleasure, and plays a key role in the process learning.

So the researchers set up a similar system in six neuroscientific post-learning experiments, comparing its performance to those of animals that had undergone the same tests. One of the tests, also known as the Harlow Experiment, had the algorithm choose two randomly selected images, one of which was associated with a reward. In the original experiment, a group of monkeys very quickly learned a strategy for of rewards. They chose an object at random the first time, but immediately after the objects that had the reward.

Ο αλγόριθμος λειτούργησε λίγο πολύ όπως λειτούργησαν και τα ζώα, επιλέγοντας εικόνες που συνδεόταν άμεσα με ανταμοιβές από νέες εικόνες που δεν είχε “ξαναδεί”. Επιπλέον, οι ερευνητές σημείωσαν ότι η μάθηση πραγματοποιήθηκε μέσω του νευρωνικού δικτύου, υποστηρίζοντας τη that dopamine plays a key role in post-learning.

The study of dopamine shows that medical science has much to gain from neural network research, just like computer science.

"Utilizing data from AI that can be applied to explain findings in neuroscience and psychology emphasizes the value of each field to the other," says the DeepMind team. "Going forward, we expect many benefits from the opposite direction, having instructions from this particular organization of brain circuits for the design of new models that learn from enhanced AI."

iGuRu.gr The Best Technology Site in Greecefgns

every publication, directly to your inbox

Join the 2.087 registrants.

Written by giorgos

George still wonders what he's doing here ...

Leave a reply

Your email address is not published. Required fields are mentioned with *

Your message will not be published if:
1. Contains insulting, defamatory, racist, offensive or inappropriate comments.
2. Causes harm to minors.
3. It interferes with the privacy and individual and social rights of other users.
4. Advertises products or services or websites.
5. Contains personal information (address, phone, etc.).