The artificial brain that learns better than humans

This is the neural network of DeepMind, a company specialized in artificial intelligence that was acquired by Google due to its merits in this field.

Just playing video games for now. Science goes step by step. DeepMind engineers have built an artificial neural network with the ability to learn and make decisions based on the knowledge acquired. In this case it is applied to video games, a field where researchers they can comfortably experiment and evaluate the reactions of the system, and then compare it with those that occur in a human brain.

The tests that the DeepMind artificial brain underwent consisted of playing to 49 different arcade video games from the 70s, which included mythical titles such as Pong and Space Invanders. The system was not specifically programmed to play video games, it was simply imbued with the ability to learn. Here it is worth making a fundamental distinction, which marks the difference between artificial intelligence and an ordinary software algorithm, such as Deep Blue, which defeated the chess champion Gary Kasparov.

In this case, the DeepMind system starts to play and learns as you practice, just like a person would. In this way he achieves such a degree of mastery in video games that is able to beat human professionals. However, each new game requires new training. The system always starts over from scratch, as it is not capable of transferring previously acquired knowledge to the new setting, as a person does.

His learning method is similar to what a person demonstrates. The artificial brain receives stimuli –In this case, the score assigned by the video game in each game– and analyze your plays based on this data. The mixture of these two variables results in the following decision making.

Two basic technologies

Deepmind, which was acquired last year by Google, has based its neural network on two artificial intelligence technologies. The first is the machine learning or machine learning, which uses an architecture inspired by the brain, in which the connections between layers of simulated neurons are strengthened based on experience. In this way the system can extract complex information from unstructured fragments. A quality that Google has deepened due to the great interest it has for its online advertising business.

The second technology is called ‘reinforcement learning‘. This term, which is used in psychology to define the positive reinforcement that is practiced with people to encourage them to do things well, tries to mimic the neural reward system in an animal. It is therefore a matter of reinforcing the knowledge learned to avoid making mistakes.

The DeepMind artificial brain has among its objectives the study of the human brain. For this reason, among other reasons, videogames have been chosen as a field of experimentation. Well, it is easier to assimilate the activity of neurons in this way, since this way the study can be compartmentalized, checking how the different parts of the system work with each action of the player-machine.

Images: Space Invanders and thelunch_box