Program Outline
Applications of AI for Anomaly Detection
Teaches anomaly detection using accelerated XGBoost, autoencoders, and GAN-based techniques on large datasets.
Delivery
Virtual, On-site, or Hybrid
Duration
8 hours
Product
RAPIDS, TensorFlow, Keras
Role
Data Scientist
NVIDIA
Deep LearningApplications of AI for Anomaly Detection
RAPIDS, TensorFlow, Keras
Best Fit
Audience Profile
Who This Program Is For
Built for teams applying AI to anomaly-heavy operational datasets.
Overview
Program Summary
Official NVIDIA DLI workshop covering supervised and unsupervised anomaly detection with accelerated ML and deep learning techniques.
Program Outcomes
After this program, participants will be able to...
Apply anomaly detection methods across large datasets
Use accelerated ML and deep learning models effectively
Delivery Formats
Enterprise Suitability
Course Outline
Complete Module Sequence
Review the full module sequence for this program, including the primary topic coverage in each module where available.
1Module 1
Build anomaly-detection solutions
+
Module 1
Build anomaly-detection solutions
Learn anomaly modeling patterns with accelerated ML and deep learning approaches.
- Supervised anomaly detection
- Unsupervised anomaly detection
- Deep-learning anomaly patterns
Coverage Areas
Topic Coverage
Coverage Item 1
Supervised anomaly detection
Coverage Item 2
Unsupervised anomaly detection
Coverage Item 3
Deep-learning anomaly patterns
Customization
Adapt This Program for Your Team
We can adapt this program around your team structure, platform priorities, delivery goals, and the scenarios your people need to work through in practice.
- •Use your anomaly use case
- •Add operational deployment patterns
