Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5

Article  Training machines to learn more like humans do

#1
C C Offline
https://www.eurekalert.org/news-releases/988754

INTRO: Imagine sitting on a park bench, watching someone stroll by. While the scene may constantly change as the person walks, the human brain can transform that dynamic visual information into a more stable representation over time. This ability, known as perceptual straightening, helps us predict the walking person’s trajectory.

Unlike humans, computer vision models don’t typically exhibit perceptual straightness, so they learn to represent visual information in a highly unpredictable way. But if machine-learning models had this ability, it might enable them to better estimate how objects or people will move.

MIT researchers have discovered that a specific training method can help computer vision models learn more perceptually straight representations, like humans do. Training involves showing a machine-learning model millions of examples so it can learn a task.

The researchers found that training computer vision models using a technique called adversarial training, which makes them less reactive to tiny errors added to images, improves the models’ perceptual straightness.

The team also discovered that perceptual straightness is affected by the task one trains a model to perform. Models trained to perform abstract tasks, like classifying images, learn more perceptually straight representations than those trained to perform more fine-grained tasks, like assigning every pixel in an image to a category.

For example, the nodes within the model have internal activations that represent “dog,” which allow the model to detect a dog when it sees any image of a dog. Perceptually straight representations retain a more stable “dog” representation when there are small changes in the image. This makes them more robust.

By gaining a better understanding of perceptual straightness in computer vision, the researchers hope to uncover insights that could help them develop models that make more accurate predictions. For instance, this property might improve the safety of autonomous vehicles that use computer vision models to predict the trajectories of pedestrians, cyclists, and other vehicles... (MORE - details)

PAPER: https://openreview.net/pdf?id=4cOfD2qL6T
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Research Perspective paper explores the debate over sentient machines C C 1 54 Feb 3, 2024 08:02 PM
Last Post: Magical Realist
  Article Some neural networks learn language like humans C C 0 69 May 24, 2023 02:31 PM
Last Post: C C
  Why AI must learn to forget C C 1 148 Nov 24, 2022 12:20 AM
Last Post: confused2
  Neurons in a dish learn to play Pong. What does it mean? Ethical concerns? C C 0 76 Feb 23, 2022 07:45 PM
Last Post: C C
  The new oracles & gods: When people trust computers more than other humans C C 0 118 Apr 14, 2021 07:08 PM
Last Post: C C
  It takes a lot of energy for machines to learn Leigha 4 294 Jan 15, 2021 02:06 PM
Last Post: confused2
  Helping machines perceive some laws of physics C C 0 214 Dec 3, 2019 04:29 AM
Last Post: C C
Question Can a robot learn right from wrong? Leigha 7 578 Jul 14, 2019 07:05 PM
Last Post: Leigha
  What artificial brains can teach us about how real brains learn C C 1 325 Oct 1, 2017 11:22 PM
Last Post: Syne
  Artificial intelligence researchers must learn ethics C C 0 451 Sep 1, 2017 05:39 PM
Last Post: C C



Users browsing this thread: 1 Guest(s)