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
via Google News
The Latest on: Learning robot
- Behind those headlines. Why not to rely on claims robots threaten half our jobson October 30, 2019 at 11:51 am
The study authors asked a group of machine learning experts to identify jobs from a long list that could be automated. The experts concluded that half of the jobs on the list could be done by robotics ...
- NASA will use a robot to listen out for danger on the ISSon October 30, 2019 at 11:36 am
including deep-learning AI. The system will be attached to an autonomous Astrobee robot that flies around the station and assists astronauts in their tasks throughout the day. The hope is that it will ...
- A robot puppet can learn to walk if it’s hooked up to human legson October 30, 2019 at 11:25 am
Humans could have guided robots to navigate around the site more accurately, from a safe distance. And while there’s currently no machine learning involved in the process, Ramos believes the data ...
- KinderLab Introduces KIBO Robotics Course for the Youngest Homeschoolerson October 30, 2019 at 10:30 am
and includes use of a KIBO 18 Robot Kit to support the curriculum. This unique rental program makes creative, cross-curricular STEM/STEAM learning affordable and easy to implement for homeschool ...
- Improving emergency response operations with adaptive learning and robotson October 30, 2019 at 7:27 am
Their project, “Learning Environments with Advanced Robotics for Next-Generation Emergency Responders (LEARNER),” focuses on integrating innovative robotics and augmented/virtual reality (AR/VR) ...
- 5G Is For Robotson October 30, 2019 at 7:05 am
We can expect these microwave modems and antennas to fall similarly. Todays Robots Store Their Memories Somewhere Else Lets look at a modern robot. We’ve had a machine learning boom these last few ...
- The Misty II Platform Robot Is Now Available for Purchaseon October 30, 2019 at 6:03 am
Misty Robotics is a spin-out of Sphero, the industry leader in EdTech robotics and STEM-based learning. Based in Boulder, Colorado, the company is financially backed by Venrock, Foundry Group and ...
- Robot-assisted Nipple-sparing Mastectomy with Immediate Breast Reconstruction: An Initial Experienceon October 30, 2019 at 3:20 am
The learning curve presented as a cumulative sum graph showed that the console time ... In the gasless method, the retractor was hung to lift the skin flap, and the robot was docked on the ...
- Meet The Robots Working The Candy Aisle This Halloweenon October 29, 2019 at 9:09 pm
CBO of Bossa Nova Robotics, to discuss how they’re leveraging AI, machine learning, computer vision and data analytics to help grocers achieve retail efficiency. What follows is an edited transcript ...
- Meet Miko 2, an adorable robot for kids that’s coming to North Americaon October 29, 2019 at 3:33 pm
A bestselling, cute educational robot has been hanging out in Asia for the last four years, and now it’s coming to North America, just in time for the holiday season. Miko 2 offers play-based learning ...
via Bing News