Course: Graph Neural Networks (GNN's)
duration: 4 hours |
Language: English (US) |
access duration: 90 days |

Details
Graph neural networks (GNNs) have recently become widely applied graph-analysis tools as they help capture indirect dependencies between data elements. This course teaches you about the different tools and functions of these GNNs. Start with an introductory part where you’ll learn how to transform graph data for use in these networks, what the use cases for machine learning in analyzing graph data are, and the challenges around modelling graphs for use in neural networks, including the use of adjacency matrices and node embeddings. In addition, you’ll learn how to build, train, and evaluate a multi-label classification model using a graph convolutional network (GCN) constructed using the Spektral Python library.
Result
After completing this course, you’ll have a good understanding of the functions of Graph Neural Networks. And you’ll be able to classify Graph Nodes with the Spektral Library.
Prerequisites
No formal prerequisites. Some prior knowledge about Graph Neural Networks is recommended.
Target audience
Network Administrator, Software Developer
Content
Graph Neural Networks (GNN's)
GNNs: An Introduction to Graph Neural Networks
- Graph neural networks (GNNs) have recently become
- widely applied graph-analysis tools as they help capture indirect dependencies between data elements. Take this course to learn how to transform graph data for use in GNNs.
- Explore the use cases for machine learning in analyzing graph data and the challenges around modeling graphs for use in neural networks, including the use of adjacency matrices and node embeddings. Examine how a convolution function captures the properties of a node and those of its neighbors. While doing so explore normalization concepts, including symmetric normalization of adjacency matrices.
- Moving along, work with the Spektral Python library to model a graph dataset for application in a GNN. Finally, practice defining a convolution function for a GNN and examine how the resultant message propagation works.
- Upon completion you'll have a clear understanding of the need for and challenges around using graph data for machine learning and recognize the power of graph convolutional networks (GCNs).
GNNs: Classifying Graph Nodes with the Spektral Library
Machine learning (ML) models can be used to extract insights
- from your graph data. Use this course to learn how to build, train,
- and evaluate a multi-label classification model using a graph
- convolutional network (GCN) constructed using the Spektral Python
- library. Begin by structuring a Spektral dataset for machine
- learning and learn how data is modeled using an adjacency matrix
- and feature vectors. Explore how to assign instances of your data
- to training, validation, and test sets using masks applied to your
- dataset instance. Construct a graph neural network (GNN) with input
- layers for the adjacency matrix and features and a GCN
- convolutional layer and use it to perform node classification.
- Discover how node features, the edges of the graph, and the
- structure of the neural network affect the performance of the
- classification model. Upon completion, you’ll be able to prepare a
- graph structure for use in an ML model and define the factors which
- can improve the accuracy of model predictions.
Course options
We offer several optional training products to enhance your learning experience. If you are planning to use our training course in preperation for an official exam then whe highly recommend using these optional training products to ensure an optimal learning experience. Sometimes there is only a practice exam or/and practice lab available.
Optional practice exam (trial exam)
To supplement this training course you may add a special practice exam. This practice exam comprises a number of trial exams which are very similar to the real exam, both in terms of form and content. This is the ultimate way to test whether you are ready for the exam.
Optional practice lab
To supplement this training course you may add a special practice lab. You perform the tasks on real hardware and/or software applicable to your Lab. The labs are fully hosted in our cloud. The only thing you need to use our practice labs is a web browser. In the LiveLab environment you will find exercises which you can start immediately. The lab enviromentconsist of complete networks containing for example, clients, servers,etc. This is the ultimate way to gain extensive hands-on experience.
Sign In
WHY_ICTTRAININGEN
Via ons opleidingsconcept bespaar je tot 80% op trainingen
Start met leren wanneer je wilt. Je bepaalt zelf het gewenste tempo
Spar met medecursisten en profileer je als autoriteit in je vakgebied.
Ontvang na succesvolle afronding van je cursus het officiële certificaat van deelname van Icttrainingen.nl
Krijg inzicht in uitgebreide voortgangsinformatie van jezelf of je medewerkers
Kennis opdoen met interactieve e-learning en uitgebreide praktijkopdrachten door gecertificeerde docenten
Orderproces
Once we have processed your order and payment, we will give you access to your courses. If you still have any questions about our ordering process, please refer to the button below.
read more about the order process
Een zakelijk account aanmaken
Wanneer u besteld namens uw bedrijf doet u er goed aan om aan zakelijk account bij ons aan te maken. Tijdens het registratieproces kunt u hiervoor kiezen. U heeft vervolgens de mogelijkheden om de bedrijfsgegevens in te voeren, een referentie en een afwijkend factuuradres toe te voegen.
Betaalmogelijkheden
U heeft bij ons diverse betaalmogelijkheden. Bij alle betaalopties ontvangt u sowieso een factuur na de bestelling. Gaat uw werkgever betalen, dan kiest u voor betaling per factuur.

Cursisten aanmaken
Als u een zakelijk account heeft aangemaakt dan heeft u de optie om cursisten/medewerkers aan te maken onder uw account. Als u dus meerdere trainingen koopt, kunt u cursisten aanmaken en deze vervolgens uitdelen aan uw collega’s. De cursisten krijgen een e-mail met inloggegevens wanneer zij worden aangemaakt en wanneer zij een training hebben gekregen.
Voortgangsinformatie
Met een zakelijk account bent u automatisch beheerder van uw organisatie en kunt u naast cursisten ook managers aanmaken. Beheerders en managers kunnen tevens voortgang inzien van alle cursisten binnen uw organisatie.
What is included?
Certificate of participation | Yes |
Monitor Progress | Yes |
Award Winning E-learning | Yes |
Mobile ready | Yes |
Sharing knowledge | Unlimited access to our IT professionals community |
Study advice | Our consultants are here for you to advice about your study career and options |
Study materials | Certified teachers with in depth knowledge about the subject. |
Service | World's best service |
Platform
Na bestelling van je training krijg je toegang tot ons innovatieve leerplatform. Hier vind je al je gekochte (of gevolgde) trainingen, kan je eventueel cursisten aanmaken en krijg je toegang tot uitgebreide voortgangsinformatie.

FAQ
Niet gevonden wat je zocht? Bekijk alle vragen of neem contact op.