Imagine that everything in your mind had been erased, and you had to learn everything all over again. What would that process be like?
Two researchers at NTNU have made a robot that learns like a young child. At least, that’s the idea. The machine starts with nothing — it has to learn everything from scratch.
“We’re still pretty far away from accurately modelling all aspects of a living child’s brain, but the algorithms that handle sound and image processing are inspired by biology,” says Professor Øyvind Brandtsegg at NTNU.
The machine is called [self.]. It analyses sound through a system based on the human ear, and learns to recognize images using a digital model of how nerve cells in the brain handle sensory impressions. It is designed to learn entirely from sensory input with no pre-defined knowledge database, so that its learning process will resemble that of a human child in early life.
“We’ve given it almost no pre-defined knowledge on purpose,” Brandtsegg says.
The ‘we’ that Brandtsegg refers to is himself and postdoc Axel Tidemann – because this is without a doubt an interdisciplinary project. The machine is so complex that cooperation between different research fields is an absolute necessity to get it to work. Brandtsegg is at the Department of Music, while Tidemann is at the Department of Computer and Information Science. But they have overlapping interests.
“We understand just enough of each other’s fields of study to see what is difficult, and why,” Brandtsegg says. Naturally, his main interest is music.
But he is also an accomplished programmer, and uses this knowledge to make music. Conversely, Tidemann made a drumming robot for his doctoral project. The robot simulated the playing styles of living drummers.
In the beginning, their robot knew nothing. It ‘hears’ sounds from a person speaking, and can connect these to a simultaneous video feed of the speaker.
The robot picks a sound that the person appears to be emphasizing, and responds by playing other sounds that it associates with this, while projecting a neural representation of its association between the sound and pictures. It doesn’t show a video, but rather how its ‘brain’ connects sounds and images.
The robot has already been on display in Trondheim and Arendal, where visitors were able to affect its learning. It was in Trondheim for a month before Christmas, and in Arendal for two weeks in January.
Interacting with a diverse audience allowed the researchers to see exactly how it learns.
There was a lot of “My name is…” and “What is your name?” from the audience, but some people sang, and others read poems.
This resulted in a period where a lot of similar sounds and connected people got mixed up, a chaos of the machine making strange connections. But this changed the more it learned.
The robot gradually absorbed more and more impressions of different people. Certain people, like guides, affected it more, because it ‘saw’ them often. The robot also learned to filter input.
If a word is said in a certain way five times, and then in a different way once, it learned to filter away the standout and concentrate on the most common way, which is presumably correct. This processing happens during the robot’s downtime.
“We say that the machine ‘dreams’ at night,” Brandtsegg says.
After a while, the robot was able to connect words and pictures together in a more complex manner— you could say that it associates sounds with images and connects them by itself.
The robot is constantly under development, and Brandtsegg and Tidemann have lost a lot of sleep over it.
“The day before it was put on display in Trondheim, we worked through the night until eight in the morning. Then we went home, ate breakfast, and went back to work at 11,” Brandtsegg says.
Between the two displays, they worked on improving the way the robot organizes its memories.
“Every little change we make takes a lot of time, at least if we want to make sure that we don’t destroy any of the things it already has learned,” Brandtsegg explains.
The result is a robot that shows how it makes associations in a very pedagogical manner. It doesn’t resemble any living organisms on purpose— you’re supposed to concentrate on its learning and the process behind it.
The Latest on: Learning robot
[google_news title=”” keyword=”Learning robot” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Learning robot
- This new transformer robot can help nuclear decommissioningon October 1, 2023 at 6:08 am
Scientists at the University of Bristol unveil a new type of robot that is capable of transforming in shape and size, thanks to adjustable struts.
- Coast Line | Robotics club hold open house events in Freedom, Santa Cruzon September 29, 2023 at 7:41 pm
Club members are able to collaboratively design and build an underwater robot, learning skills such as 3D design, coding and laser-cutting. Participants will then be able to form a team to compete in ...
- The 17 Best Robot Movies of All Timeon September 29, 2023 at 7:30 am
to include two newer robot movies, including The Creator ... looking for acceptance, and learning what it means to love. And it’s beautiful. Paul Verhoeven’s masterpiece is a lot funnier than you ...
- Farm robots inspired by ant brainson September 28, 2023 at 10:19 am
With the rapid-paced rise of AI in everyday life, nothing, not even the traditional farmer, is untouched by the technology.
- Nvidia is Making Safer Robots for the Factory Flooron September 28, 2023 at 9:00 am
Nvidia wants its manufacturing robots to lend a helping hand – or get out of the way. The chip giant is seeking to patent a system ...
- How Generative AI Can Accelerate The Deployment Of Autonomous Robotson September 28, 2023 at 5:15 am
Let's explore seven opportunities for using generative AI in accelerating robot deployment by tackling some of its most notable challenges and steps.
- FedEx’s New Robot Loads Delivery Trucks Like It’s Playing 3D Tetrison September 27, 2023 at 1:59 pm
FedEx handles over 15 million packages daily. A two-armed, AI-infused robot is now helping pack some of them into delivery trucks with expert care.
- Tesla’s Humanoid Robot Can Do Yoga Nowon September 27, 2023 at 1:30 pm
The Tesla Optimus is ready to stretch its legs. Elon Musk’s company recently shared a video of the latest version of its humanoid robot. The clip, which was posted to X, shows just how far the bipedal ...
- Figure's Brett Adcock on the practicalities of humanoid robot workerson September 27, 2023 at 8:00 am
A year and a bit into Figure's push toward humanoid robot laborers, founder Brett Adcock talks to us about how they'll enter the workforce, how they're being trained, how language model AIs will be ...
- AI-Powered Tesla’s Optimus Robot Outpaces Competitors with Ten Key Advancementson September 25, 2023 at 3:30 am
In a stunning display of cutting-edge robotics, Tesla’s Optimus robot has taken the world by storm with its remarkable capabilities, leaving even industry stalwarts like Boston Dynamics’ Atlas in its ...
via Bing News