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
- UBTECH’s iPhone-enabled Iron Man Robot battles boredom at $150 (Save $50)on March 23, 2020 at 10:40 am
If you can live without the Avengers crossover, then there are plenty of savings to be had going with UBTECH’s JIMU Robot Builderbots Kit instead. You’ll pocket an extra $96 by going with this ...
- Feeling stressed? Playing Pictionary with a robot might helpon March 22, 2020 at 10:22 am
It’s basically playing Pictionary with a robot, okay? ‘Help teach it by adding your drawings to the world’s largest doodling data set, shared publicly to help with machine learning research,’ reads ...
- Diligent Robotics Announces $10M Series A Fundingon March 21, 2020 at 5:39 pm
Diligent Robotics, the A.I. company building socially intelligent robots for the future of work, announced that it has raised a $10 million series A investment, led by DNX Ventures, and participation ...
- Chinese robot maker sees demand surge amid coronaviruson March 20, 2020 at 5:30 pm
BEIJING — While other industries struggle, Liu Zhiyong says China’s virus outbreak is boosting demand for his knee-high, bright-yellow robots to deliver groceries and patrol malls looking for shoppers ...
- Google taps computer vision to improve robot manipulation performanceon March 20, 2020 at 4:06 pm
They then tasked a real-world robot with learning to grasp a set of objects through trial and error. Initially, there weren’t significant performance gains compared with training the affordance models ...
- Astro Boy (1980) - The Top 10 Robots From The Anime (Who Are Not Astro)on March 20, 2020 at 1:38 pm
Astro Boy is a story of not only pop-culture prominence but also of influence. The manga, by the great Osamu Tezuka, first appeared as Tetsuwan Atom (Mighty Atom) in Shōnen during April 1952 and was ...
- Hospital droid Diligent Robotics raises $10M to assist nurseson March 20, 2020 at 12:10 pm
“The team continues to demonstrate unmatched robotics-specific innovation by combining social intelligence and human-guided learning capabilities” says True Ventures partner and Diligent board member ...
- Learning About Robots and Cobotson March 20, 2020 at 6:34 am
Robots and collaborative/cooperative robots, or cobots, are becoming more common and more functional every day. They dominate many assembly lines and have change the way warehouses work. We have a lot ...
- Seen, stored, learned - Self-learning robots solve tasks with the help of an Ensenso 3D cameraon March 20, 2020 at 5:20 am
Trying out different behaviours is one of the classic learning methods. Success or failure decides which behaviour is adopted. This principle can be transferred to the world of robots. At the ...
- 2020 Innovations in Prosthesis, Solar Cells & Panels, Milk Quality Sensors, Neuromorphic Capacitors, Robots, and 3D Printing - ResearchAndMarkets.comon March 20, 2020 at 3:57 am
Robots, and 3D Printing" report has been added to ResearchAndMarkets.com's offering. This edition of the Inside R&D TechVision Opportunity Engine (TOE) features trends and innovations in diabetes ...
via Bing News