Twitter
Advertisement

Artificial neural network learns human language

Researchers from the University of Sassari (Italy) and the University of Plymouth (UK) have developed a cognitive model, made up of two million interconnected artificial neurons, able to learn to communicate using human language.

Latest News
article-main
Credits: Bruno Golosio
FacebookTwitterWhatsappLinkedin

Scientists are still puzzled about how our brain develops the ability to perform complex cognitive functions, like those needed for language and reasoning.

Researchers from the University of Sassari (Italy) and the University of Plymouth (UK) have developed a cognitive model, made up of two million interconnected artificial neurons, able to learn to communicate using human language.

The human brain has about one hundred billion neurons that communicate by means of electrical signals.

We might think that the brain works in a similar way to a computer: after all, even computers work through electrical signals.

Computers work through programs developed by human programmers.  These programs have coded rules that the computer must follow to perform a given task. However, there is no evidence of the existence of such programs in our brain. 

A cognitive model made up of two million interconnected artificial neurons was able to learn to communicate using human language starting from a state of "tabula rasa", through communication with a human interlocutor. 

The model is called ANNABELL (Artificial Neural Network with Adaptive Behavior Exploited for Language Learning) and it is described in PLOS ONE.  

The ANNABELL model is entirely made up of interconnected artificial neurons.

The model is able to learn, due to synaptic plasticity, to control the signals that open and close the neural gates, so as to control the flow of information among different areas.

ANNABELL does not have pre-coded language knowledge; it learns only through communication with a human interlocutor.

The cognitive model has been validated using a database of about 1500 input sentences, based on literature on early language development, and has responded by producing a total of about 500 sentences in output, containing nouns, verbs, adjectives, pronouns, and other word classes, demonstrating the ability to express a wide range of capabilities in human language processing.

Read full article here.

Find your daily dose of news & explainers in your WhatsApp. Stay updated, Stay informed-  Follow DNA on WhatsApp.
Advertisement

Live tv

Advertisement
Advertisement