Graph Neural Networks & Knowledge Graphs

What you'll learn

• Building and evaluating ML models
• Preparing data for training
• Tuning model performance
• Deploying models to production
• Understand neural network architectures
• Understand supervised and unsupervised learning

Planned outline shown above (sample metadata). The detailed module and lesson list for this course hasn't been published yet.

Description

Explore GNNs and knowledge graphs for recommendation systems, drug discovery, and fraud detection. Build with PyTorch Geometric and Neo4j.

What this course covers: Graph Neural Networks & Knowledge Graphs works through neural network architectures, supervised and unsupervised learning, feature engineering and data preparation and deploying and monitoring models.

Skills you will build: tuning model performance, deploying models to production and preparing data for training.

Practical applications: prediction and classification systems, computer vision and NLP applications and AI features inside products.

Who should take this course: developers, data analysts and engineering students moving into machine learning and AI. It is designed for learners with solid experience in machine learning and AI who want advanced, in-depth practice.

Learning outcomes: by the end of the course you should be able to apply neural network architectures and tuning model performance to your own work or projects, and know which areas to practise next.

Requirements

• Solid working knowledge of machine learning and AI
• Comfort with intermediate concepts
• A computer with internet access

Your instructor

• M
  Meghna J. ★★★★★ 5.0/5 Sample review

  Clear structure from feature engineering and data preparation through to deploying and monitoring models. I'd like a few more practice tasks, but overall very useful. Loved that model evaluation got as much attention as model building.

• H
  Harsh L. ★★★★★ 4.5/5 Sample review

  Well organised. Revisiting the feature engineering and data preparation part a second time really helped it click. The deployment section filled a gap most ML courses skip.

• A
  Aarav M. ★★★★★ 4.5/5 Sample review

  Good balance of theory and practice. The neural network architectures lessons helped me apply tuning model performance in real situations. The hands-on notebooks made backpropagation finally make sense to me.

Sample reviews are illustrative demo content, not verified purchases. Ratings from learners will appear here once submitted.