Teach Neural Networks to identify sequences of values
Off We Go!
The compile()
method then readies the learning model for processing, determines mean_squared_error
(deviations from optimal learning success are measured according to the mean square method) as the learning parameter, and sets rmsprop
, a common method for neural networks, as the algorithm optimizer
.
Line 45 then calls the model's fit()
method, passes the learning data to it, and stipulates the number of learning iterations as epoch = 500
. In my lab, a lower number affected the results negatively, but larger values of epoch
did not achieve any greater learning success, since the system reached a steady state afterward, and the learning process visibly stagnated at a constant value for the loss
function.
The section starting in line 48 of Listing 1 then monitors the predictions with the model in the current phase in the training, both for the training data and for previously unseen sequences that the system needs to guess without precedence in the training data.
Figure 7 shows that the network does a good job, even for cyclic data (1,2,3,1,2,3), regardless of the length of the signal period, which is a major advantage over traditional neural networks, for which you have to state the periodicity in advance for reliable predictions.
![](/var/linux_magazin/storage/images/issues/2018/206/programming-snapshot-ai-sequences/figure-7/718685-1-eng-US/Figure-7_large.png)
Fast as a Snail
You need to install the following libraries from the Python treasure trove to be able to install the keras
library:
pip3 install --user keras pandas tensorflow sklearn numpy sudo apt-get install python-tk
The TensorFlow back end used by keras
is not exactly speedy; it took a good 10 seconds for the program to get going and start the training on my five-year-old PC.
At the end of the day, the network did not perform particularly well in the intelligence test (Figure 8; see also the "Online Example" box). As you will have guessed, you need to alternately add 3 and 2 to the existing numbers in the 2,5,7,10,12
series. Since the jump from 10 to 12 was two units in length, a count of three thus needs to be added to predict the next number: 15 is the correct result. The network tended toward 14 most of the time, so it cannot compete with human intelligence (as of yet).
![](/var/linux_magazin/storage/images/issues/2018/206/programming-snapshot-ai-sequences/figure-8/718688-1-eng-US/Figure-8_large.png)
Online Example
Mike Schilli demonstrates the example in a screencast (in German) at: http://www.linux-magazin.de/Ausgaben/2017/10/plus
Infos
- Number sequence test: https://www.fibonicci.com/numerical-reasoning/number-sequences-test/easy/
- Listings for this article: ftp://ftp.linux-magazine.com/pub/listings/linux-magazine.com/206/
- Brownlee, Jason. Long Short-Term Memory Networks with Python: Machine Learning Mastery. 2017, https://machinelearningmastery.com/lstms-with-python/
« Previous 1 2
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.
![Learn More](https://www.linux-magazine.com/var/linux_magazin/storage/images/media/linux-magazine-eng-us/images/misc/learn-more/834592-1-eng-US/Learn-More_medium.png)
News
-
NVIDIA Released Driver for Upcoming NVIDIA 560 GPU for Linux
Not only has NVIDIA released the driver for its upcoming CPU series, it's the first release that defaults to using open-source GPU kernel modules.
-
OpenMandriva Lx 24.07 Released
If you’re into rolling release Linux distributions, OpenMandriva ROME has a new snapshot with a new kernel.
-
Kernel 6.10 Available for General Usage
Linus Torvalds has released the 6.10 kernel and it includes significant performance increases for Intel Core hybrid systems and more.
-
TUXEDO Computers Releases InfinityBook Pro 14 Gen9 Laptop
Sporting either AMD or Intel CPUs, the TUXEDO InfinityBook Pro 14 is an extremely compact, lightweight, sturdy powerhouse.
-
Google Extends Support for Linux Kernels Used for Android
Because the LTS Linux kernel releases are so important to Android, Google has decided to extend the support period beyond that offered by the kernel development team.
-
Linux Mint 22 Stable Delayed
If you're anxious about getting your hands on the stable release of Linux Mint 22, it looks as if you're going to have to wait a bit longer.
-
Nitrux 3.5.1 Available for Install
The latest version of the immutable, systemd-free distribution includes an updated kernel and NVIDIA driver.
-
Debian 12.6 Released with Plenty of Bug Fixes and Updates
The sixth update to Debian "Bookworm" is all about security mitigations and making adjustments for some "serious problems."
-
Canonical Offers 12-Year LTS for Open Source Docker Images
Canonical is expanding its LTS offering to reach beyond the DEB packages with a new distro-less Docker image.
-
Plasma Desktop 6.1 Released with Several Enhancements
If you're a fan of Plasma Desktop, you should be excited about this new point release.