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
- Pandemic Tantrums? Enter the Robot Playmate for Kidson August 4, 2020 at 5:04 am
Early childhood development experts and robotics engineers are working together to create robots aimed at helping young children regulate their emotions and develop social and emotional skills at home ...
- Robot use on the rise during pandemic, experts sayon August 3, 2020 at 4:30 pm
From hospital robots to a White Castle employee named Flippy, robot use and demand have increased during the COVID-19 pandemic, experts say.
- Amazon slashes up to 45% off Sphero’s Coding Robots, now priced from $27on August 3, 2020 at 11:46 am
Amazon is offering the Sphero Mini Robot Soccer Ball for $27 shipped. That’s up to $23 off the typical rate there and beats the lowest price we have tracked by $1. Once equipped with this miniature ...
- Top 5 Robotics and Artificial Intelligence Stocks To Buy According to Hedge Fundson August 2, 2020 at 9:42 am
What are the best robotics and artificial intelligence stocks to buy today? In this time of uncertainty characterized by volatile market movements, economic contraction, and spiraling unemployment, ...
- UNI AMC first to purchase cutting-edge robotics equipmenton August 2, 2020 at 8:21 am
The University of Northern Iowa Additive Manufacturing Center (UNI AMC) recently became the first university-based center in the world to purchase a cutting-edge piece of robotics equipment, ...
- iRobot Root rt0 debuts as the latest Swift coding robot with 20 sensors in towon July 29, 2020 at 1:43 pm
The release of iRobot Root rt0 is timed well as it's being marketed as a solution that brings "classroom learning into the home." ...
- California students program robots remotely during distance learningon July 29, 2020 at 12:24 pm
A pair of enterprising Compton summer school instructors used cameras and a giant world map to let students command their robots' travels between nations.
- Global Programmable Robots market is expected to reach $8,083.61 million by 2027on July 29, 2020 at 11:57 am
Some of the key players profiled in the Programmable Robots Market include Aldebaran Robotics Sas, Fischertechnik GmbH, Honda Motor Co., Ltd, Innovation First International Inc, iRobot Corporation, ...
- Add Coding to Your Family Game Night with the New iRobot® Root® rt0 Coding Roboton July 29, 2020 at 3:29 am
Robot Corp. (NASDAQ: IRBT), the leader in consumer robots, today expanded its educational product offerings with the launch of the Root® rt0 coding robot, an easy-to-use and customizable coding robot ...
- A Robot Factory or Digital Workers Powered by Machine Learning to Be Introduced by Russia's OTB Bank to Read, Comprehend, Process Financial Documentson July 22, 2020 at 4:34 pm
The robots are expected to help with document processing and data ... These digital employees will reportedly use machine learning and optical character recognition (OCR) to fully automate routine ...
via Bing News