Teach Neural Networks to identify sequences of values
First Things First

2, 5, 7, 10, 12 – and what number comes next? Mike Schilli tests whether intelligence tests devised by psychologists can be cracked with modern AI Networks.
Neural networks do great things when it comes to detecting patterns in noisy input data and assigning unambiguous results to them. If a dozen people with different handwriting enter the letters A or B in a form, a trained network can identify with almost 100 percent certainty what they wrote. Or consider pattern recognition systems for identifying the license plates of passing vehicles: Aren't these technical miracles? They extract the digits from a camera feed so that the Department of Transportation knows exactly who is going where.
Once a neural network is done learning, it always assigns the same result to the same input data, but when it comes to tasks that need to determine the next value in time-discrete value sequences, neural networks often fail to deliver perfect results, especially if the input signal is subject to variations of unknown periodicity.
In a neural network, the learning algorithm adjusts internal weights based on the training data. However, once these weights are determined, they won't change anymore at run time and thus cannot account for temporal changes in the input data, because the machine doesn't remember any previous state. Recurrent neural networks (RNNs) maintain internal connections back to the input, and thus a result can influence the next input vector, but this does not help a simple network identify temporal patterns that extend over several cycles.
[...]
Buy this article as PDF
(incl. VAT)
Buy Linux Magazine
Subscribe to our Linux Newsletters
Find Linux and Open Source Jobs
Subscribe to our ADMIN Newsletters
Support Our Work
Linux Magazine content is made possible with support from readers like you. Please consider contributing when you’ve found an article to be beneficial.

News
-
TuxCare Announces Support for AlmaLinux 9.2
Thanks to TuxCare, AlmaLinux 9.2 (and soon version 9.6) now enjoys years of ongoing patching and compliance.
-
Go-Based Botnet Attacking IoT Devices
Using an SSH credential brute-force attack, the Go-based PumaBot is exploiting IoT devices everywhere.
-
Plasma 6.5 Promises Better Memory Optimization
With the stable Plasma 6.4 on the horizon, KDE has a few new tricks up its sleeve for Plasma 6.5.
-
KaOS 2025.05 Officially Qt5 Free
If you're a fan of independent Linux distributions, the team behind KaOS is proud to announce the latest iteration that includes kernel 6.14 and KDE's Plasma 6.3.5.
-
Linux Kernel 6.15 Now Available
The latest Linux kernel is now available with several new features/improvements and the usual bug fixes.
-
Microsoft Makes Surprising WSL Announcement
In a move that might surprise some users, Microsoft has made Windows Subsystem for Linux open source.
-
Red Hat Releases RHEL 10 Early
Red Hat quietly rolled out the official release of RHEL 10.0 a bit early.
-
openSUSE Joins End of 10
openSUSE has decided to not only join the End of 10 movement but it also will no longer support the Deepin Desktop Environment.
-
New Version of Flatpak Released
Flatpak 1.16.1 is now available as the latest, stable version with various improvements.
-
IBM Announces Powerhouse Linux Server
IBM has unleashed a seriously powerful Linux server with the LinuxONE Emperor 5.