They are designing an Artificial Intelligence to communicate with all animals

No time to read?
Get a summary

A group of researchers from the Earth Species Project (ESP), headquartered in California, United States, plan to use machine learning. Artificial Intelligence to decipher the “languages” of animals and translate them into something humans can understandand they want to apply it to the entire animal kingdom.

While it may seem like something out of a science fiction story, the plan that researchers have compared to the 1960s lunar project is actually not new. And it has its roots in the background of long-standing human interest in the study of animal vocalizations.

For example, we know that the warning sounds of different primates vary according to the predator; We also know that dolphins communicate with characteristic whistles; and we know that some songbirds can rearrange the components of their calls to mean different things.

However, most experts avoid looking for this language because no animal communication meets all the requirements for it. In every situation, Until recently, decoding was based on careful observation.

But The Guardian reports an increase in the use of machine learning to process the huge amount of data that can be collected by contemporary animal sensors.

The project wants to understand all genres pixabay

For example, Elodiw Briefer, an associate professor of vocal communication in animals and mammals, notes: machine learning or Artificial Intelligence is now used to understand animal communication. Using the grunts of pigs, Briefer developed an algorithm to determine whether the animal was feeling happy or sad.

Another project is DeepSqueak, which analyzes ultrasonic sounds to determine if mice are under stress; There is also CETI (which stands for Cetacean Translation Initiative), which translates sperm whale communication using machine learning.

Understanding all genres with one algorithm

The California-based nonprofit Earth Species Project (ESP), which was founded in 2017 with the help of Silicon Valley investors, says its approach is different. It focuses on unraveling the communication of all, not just one species.

That’s why ESP plans to first decipher animal communication using machine learning and then make its findings available to everyone.

Aza Raskin, co-founder and president of ESP, claims to want to strengthen human bonds with other living species by using machine learning to decipher non-human communication.

“We are species-free,” Raskin told The Guardian. The translation algorithms that ESP is developing are designed to “work in biology from worms to whales.”

As The Guardian explains, dolphin trainers “together” and “create” with their hands to communicate. Before going out, trained dolphins exchange sounds, turn around, lift their tails, perform a new trick on themselves and perform.

The founder stated that it does not prove that it is a language, it would be much easier if they only had access to a linguistic means of communication.

panda bear synchronization

Thus, Raskin made sure that animals, like humans, have various forms of nonverbal communication, such as bees performing a special “wave dance” to alert each other to perch on a particular flower.

Despite the seemingly insurmountable challenges facing the group, the project has made at least some progress, such as an experimental algorithm that can detect which individual in a noisy group of animals is “talking” by default.

A second algorithm could generate simulated animal calls to “talk” to them directly. “Although we don’t know what that means yet, it’s making the AI ​​speak the language,” Raskin told The Guardian.

Although this type of research has very interesting results, not everyone is excited about the power of artificial intelligence.

For example, Robert Seyfarth of the University of Pennsylvania believes the technology could be useful for problems such as determining an animal’s vocal repertoire. But there are other areas he doubts add much to, such as exploring the meaning and function of vocalizations.

Only time will tell whether the project will be successful. What is clear is the growing role of artificial intelligence and machine learning in the future of science.

“These are tools that allow us to take off our human glasses to understand all communication systems,” says Raskin.

…..

Environment department contact address:[email protected]

No time to read?
Get a summary
Previous Article

Steam made a small but important addition – now games can be added to the library without downloading

Next Article

Bloomberg: There will be lots of ads on iPhone