Skip to main content

Reset your password

Please enter the e-mail address you used to register to reset your password

Note: The verification e-mail to change your password should arrive immediately. However, in some cases it takes longer. Don't forget to check your spam folder.

If you haven't received the e-mail in 24 hours, please contact customerservices@ioppublishing.org

Registration complete

Thank you for registering with Physics World
If you'd like to change your details at any time, please visit My account

Close
Mathematics and computation

Mathematics and computation

Neural networks, explained

09 Jul 2018
This article first appeared in the 2018 Physics World Focus on Computing

Wouldn’t it be wonderful if computers could figure out how to solve problems on their own, without precise instructions? Neural networks hold this promise, but scientists must use them with caution – or risk discovering that they have solved the wrong problem entirely, writes Janelle Shane

gravitational lenses
Generation game: Images of gravitational lenses generated by a convolutional neural network, to be used in training another neural network to identify new gravitational lenses. (From: Emergent Scientist 2 1, CC BY 4.0 J Pearson et al., published by EDP Sciences, 2018)
What are neural networks? Artificial neural networks are a form of machine-learning algorithm with a

You’ve reached the limit of what you can view on Physics World without registering

If you already have an account on Physics World, then please sign in to continue reading

If you do not yet have an account, please register so you can

  • Access more than 20 years of online content
  • Choose which e-mail newsletters you would like to receive

Janelle Shane is a research scientist in optics and author of the AI Weirdness blog about neural networks and their foibles
Read previous

The rise and rise of cryogenic electron microscopy
Read next

Precision multi-lesion phantom sharpens stereotactic radiosurgery

Discover more from Physics World

Related jobs

Related events

Copyright © 2024 by IOP Publishing Ltd and individual contributors