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.
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).
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.
News
-
Canonical Bumps LTS Support to 12 years
If you're worried that your Ubuntu LTS release won't be supported long enough to last, Canonical has a surprise for you in the form of 12 years of security coverage.
-
Fedora 40 Beta Released Soon
With the official release of Fedora 40 coming in April, it's almost time to download the beta and see what's new.
-
New Pentesting Distribution to Compete with Kali Linux
SnoopGod is now available for your testing needs
-
Juno Computers Launches Another Linux Laptop
If you're looking for a powerhouse laptop that runs Ubuntu, the Juno Computers Neptune 17 v6 should be on your radar.
-
ZorinOS 17.1 Released, Includes Improved Windows App Support
If you need or desire to run Windows applications on Linux, there's one distribution intent on making that easier for you and its new release further improves that feature.
-
Linux Market Share Surpasses 4% for the First Time
Look out Windows and macOS, Linux is on the rise and has even topped ChromeOS to become the fourth most widely used OS around the globe.
-
KDE’s Plasma 6 Officially Available
KDE’s Plasma 6.0 "Megarelease" has happened, and it's brimming with new features, polish, and performance.
-
Latest Version of Tails Unleashed
Tails 6.0 is based on Debian 12 and includes GNOME 43.
-
KDE Announces New Slimbook V with Plenty of Power and KDE’s Plasma 6
If you're a fan of KDE Plasma, you'll be thrilled to hear they've announced a new Slimbook with an AMD CPU and the latest version of KDE Plasma desktop.
-
Monthly Sponsorship Includes Early Access to elementary OS 8
If you want to get a glimpse of what's in the pipeline for elementary OS 8, just set up a monthly sponsorship to help fund its continued existence.