How does the image-recognition technology in a self-driving car respond to a blurred shape suddenly appearing on the road? Researchers from KU Leuven have shown that machines can learn to respond to unfamiliar objects like human beings would.
Imagine heading home in your self-driving car. The rain is falling in torrents and visibility is poor. All of a sudden, a blurred shape appears on the road. What would you want the car to do? Should it hit the brakes, at the risk of causing the cars behind you to crash? Or should it just keep driving?
Human beings in a similar situation will usually be able to tell the difference between, say, a distracted cyclist who’s suddenly swerving, and road-side waste swept up by the wind. Our response is mostly based on intuition. We may not be sure what the blurred shape actually is, but we know that it looks likea human being rather than a paper bag.
But what about the self-driving car? Can a machine trained to recognize images tell us what the unfamiliar shape looks like? According to KU Leuven researchers Jonas Kubilius and Hans Op de Beeck, it can.
“Current state-of-the-art image-recognition technologies are taught to recognize a fixed set of objects,” Jonas Kubilius explains. “They recognize images using deep neural networks: complex algorithms that perform computations somewhat similarly to the neurons in the human brain.”
“We found that deep neural networks are not only good at making objective decisions (‘this is a car’), but also develop human-level sensitivities to object shape (‘this looks like …’). In other words, machines can learn to tell us what a new shape – say, a letter from a novel alphabet or a blurred object on the road – reminds them of. This means we’re on the right track in developing machines with a visual system and vocabulary as flexible and versatile as ours.”
Does that mean we may soon be able to safely hand over the wheel? “Not quite. We’re not there just yet. And even if machines will at some point be equipped with a visual system as powerful as ours, self-driving cars would still make occasional mistakes – although, unlike human drivers, they wouldn’t be distracted because they’re tired or busy texting. However, even in those rare instances when self-driving cars would err, their decisions would be at least as reasonable as ours.”
The Latest on: Deep neural networks
via Google News
The Latest on: Deep neural networks
- Neural Network “Hallucinates” Protein Structureson December 2, 2021 at 2:32 am
In a report in Nature, researchers describe the development of a neural network that “hallucinates” proteins with new, stable structures.
- Neural network 'hallucinates' proteins with new, stable structureson December 1, 2021 at 7:02 pm
Just as convincing images of cats can be created using artificial intelligence, new proteins can now be made using similar tools. In a report in Nature, a team including researchers at the University ...
- Deep learning dreams up new protein structureson December 1, 2021 at 1:36 pm
Using artificial intelligence and deep learning, researchers have developed a neural network that 'hallucinates' the structures of new protein molecules. The scientists made up completely random ...
- Deep learning tool helps NASA discover 301 exoplanetson November 30, 2021 at 5:39 pm
NASA scientists used a neural network called ExoMiner to examine data from Kepler, increasing the total tally of confirmed exoplanets in the universe.
- NASA Uses Deep Learning to Add 301 Entries to Kepler's List of Exoplanetson November 30, 2021 at 2:59 am
Searching for exoplanets is a daunting task in our vast universe. That's why NASA is looking at machine learning for a little help in the search.
- A deep learning method to automatically enhance dog animationson November 26, 2021 at 9:30 am
Researchers at Trinity College Dublin and University of Bath have recently developed a model based on deep neural networks that could help to improve the quality of animations containing quadruped ...
- A Whopping 301 Newly Confirmed Exoplanets – Discovered With New Deep Neural Network ExoMineron November 25, 2021 at 4:05 am
Scientists have added a whopping 301 newly confirmed exoplanets to the total exoplanet tally. Scientists recently added a whopping 301 newly validated exoplanets to the total exoplanet tally. The ...
- 301 new exoplanets verified by deep learning with a new neural networkon November 23, 2021 at 3:02 am
Using a new deep learning neural network called ExoMiner, scientists have identified 301 new exoplanets from the Kepler Archive.
- Deep Neural Networks Find 301 More Planets Increasing Kepler's Total Counton November 22, 2021 at 8:00 am
Using a new deep neural network called ExoMiner, a team of scientists from Universities Space Research Association (USRA), NASA, and other institutions recently ...
- Jina.ai raises $30M for its for its neural search platformon November 22, 2021 at 3:00 am
Berlin-based Jina.ai, an open-source startup that uses neural search to help its users find information in their unstructured data (including videos and images), today announced that it has raised a ...
via Bing News