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
- Robot made out of tree branches learns to move on its ownon July 6, 2019 at 12:26 am
Video Courtesy: Azumi Maekawa Before the robot was made, the team weighed the branches, scanned them in 3D, and then uploaded it to a deep learning network. With this data, along with details about ... […]
- This creepy crawling robot has a skeleton made from tree brancheson July 5, 2019 at 6:35 am
The robot learned how to move using Deep Reinforcement Learning in simulation and it is proof that using found objects as the raw material to make simple robots is an idea worth exploring. ... […]
- Robotics: AUVSI Xponential Takeaways And Key Trendson July 5, 2019 at 2:47 am
Overall, mobile robotics research and development activities ... Casia detects other aircraft, uses machine learning (ML) to classify them, determines the threat posed to the vehicle, and triggers ... […]
- Drivers Of 4 Key Segments In Robotics And AIon July 5, 2019 at 1:05 am
Today, cutting-edge technologies such as vision recognition, machine-learning, failure prediction and collaborative robots (co-bots) are vastly extending the capabilities of machines and ... […]
- 5 Best Arduino Robot Kits in 2019on July 4, 2019 at 11:34 pm
As a learning tool, it does its job of being a starter kit beautifully. The Sparki Robot from ArcBotics boasts of being one of the widely used learning tools for STEM education. After all, schools ... […]
- The coolest K-12 robotics programs we saw at ISTEon July 4, 2019 at 3:09 am
but sometimes kids need a push to discover the “why” behind learning how to code. At ISTE 2019, that push to learn coding was clear as new K-12 robotics solutions emerged. Aside from the cool factor K ... […]
- UTS says RoboCup is about building robots to improve lives, not winningon July 4, 2019 at 12:12 am
and digital pen movements to better understand the link between behaviour patterns and learning outcomes. New centre will house the Southern Hemisphere's largest motion-capture device as well as a ... […]
- Save 11% on the Cytron rero:micro Coding Robot Kiton July 3, 2019 at 8:45 am
But rather than trudging through a boring bootcamp, how about learning programming the fun way with the rero:micro Coding Robot? This DIY tech kit lets you expand your STEM and coding know-how by ... […]
- Ph.D. Student Seeks to Help Children through Roboticson July 2, 2019 at 10:45 pm
Using cameras, the robots can focus on different points on the face to best determine how to analyze the subjects’ emotions. “The projects I’m working on — using artificial intelligence, machine ... […]
- ROYBI Closes $4.2M Financing in Seed Round to Bring Its AI-Powered Educational Robot to Homes and Schoolson July 2, 2019 at 7:31 am
ROYBI, the AI-powered robot dedicated to early childhood education and language learning, announced today the closing of its seed round from investors in Silicon Valley. The company plans to ... […]
via Bing News