Amazon SageMaker, machine learning on AWSAmazon SageMaker: ML on AWS

Learn machine learning workflows on AWS: prepare data, build and train models, tune them and deploy scalable ML solutions, ending with a real-world ML project.

Book an appointment Call 847-350-9034

10 modulesMLOpsReal-world project

Ten modules

From AWS and SageMaker basics to a real-world project. 1

Intro to AWS and SageMaker

Machine learning types, the AWS AI/ML ecosystem and use cases.2

Architecture

Studio, notebooks, compute options, IAM roles, storage and security.3

Data preparation

S3 datasets, Data Wrangler, feature engineering, Ground Truth.4

Training

Built-in algorithms, TensorFlow, PyTorch, Scikit-learn, distributed training.5

Tuning

Automatic model tuning, warm-start, Debugger and Profiler.6

Deployment

Real-time, batch and asynchronous inference, endpoints, auto-scaling.7

MLOps

SageMaker Pipelines, CI/CD, model registry, retraining, drift.8

Advanced features

JumpStart, Canvas, Clarify, Neo, reinforcement learning, geospatial ML.9

AWS integrations

S3, Lambda, API Gateway, EventBridge, CloudWatch, RDS, DynamoDB, EMR.10

Real-world projects

Apply everything in an end-to-end ML project.

Detailed course content

Topics in each module.

1. Introduction to AWS and SageMaker

✓Supervised, unsupervised and reinforcement learning✓Challenges in traditional ML workflows✓Key benefits of SageMaker for data scientists and engineers✓Use cases: NLP, computer vision, forecasting, fraud detection

2. Architecture and key components

✓SageMaker Studio, Studio Lab and Notebook Instances✓Compute options (CPU, GPU, accelerators)✓Domain, users and IAM roles✓Storage: S3, EFS, FSx; security: IAM, VPC, encryption

3. Data preparation

✓Importing datasets from S3✓SageMaker Data Wrangler✓Feature engineering and transformation✓Data labeling with Ground Truth and data quality monitoring

4 and 5. Training, tuning, optimization

✓Built-in algorithms and frameworks✓Estimators, hyperparameters, distributed training✓Spot instances for cost optimization✓Hyperparameter tuning jobs, Debugger and Profiler

6. Model deployment

✓Inference concepts: real-time, batch, asynchronous✓Multi-model endpoints and serverless inference✓A/B testing and blue/green deployments✓Auto-scaling, cost optimization and pricing

7 to 9. MLOps, advanced features, integrations

✓SageMaker Pipelines, CI/CD with GitHub and CodePipeline✓Model registry, automated retraining, drift monitoring✓JumpStart (pre-trained models, LLMs), Canvas, Clarify, Neo✓Lambda, API Gateway, EventBridge, CloudWatch, RDS, DynamoDB, EMR

Support and salient features

Career support and classroom features that come with the course.

Staffing support

✓Resume preparation✓Mock interview preparation✓Phone interview preparation✓Face to face interview preparation✓Project and technology preparation✓Internship with internal project work✓Externship with client project work

Our salient features

✓Hands-on labs and homework✓Group discussion and case study✓Course project work✓Regular quiz and exam✓Regular support beyond the classroom✓Students can re-take the class at no cost✓Dedicated conference rooms for group project work✓Live streaming for remote students✓Video recording to catch up on a missed class

Explore more training

See other programs, funding options and the class schedule. All training programs Education grant program Upcoming classes

Ready to start build ML on AWS?

Call 847-350-9034 or book an appointment to talk about this course and funding options.Book an appointment Call 847-350-9034 Education grant program

Ten modules

From AWS and SageMaker basics to a real-world project.1

Intro to AWS and SageMaker

Machine learning types, the AWS AI/ML ecosystem and use cases.2

Architecture

Studio, notebooks, compute options, IAM roles, storage and security.3

Data preparation

S3 datasets, Data Wrangler, feature engineering, Ground Truth.4

Training

Built-in algorithms, TensorFlow, PyTorch, Scikit-learn, distributed training.5

Tuning

Automatic model tuning, warm-start, Debugger and Profiler.6

Deployment

Real-time, batch and asynchronous inference, endpoints, auto-scaling.7

MLOps

SageMaker Pipelines, CI/CD, model registry, retraining, drift.8

Advanced features

JumpStart, Canvas, Clarify, Neo, reinforcement learning, geospatial ML.9

AWS integrations

S3, Lambda, API Gateway, EventBridge, CloudWatch, RDS, DynamoDB, EMR.10

Real-world projects

Apply everything in an end-to-end ML project.

Detailed course content

Topics in each module.1

Introduction to AWS and SageMaker

✓Supervised, unsupervised and reinforcement learning✓Challenges in traditional ML workflows✓Key benefits of SageMaker for data scientists and engineers✓Use cases: NLP, computer vision, forecasting, fraud detection2

Architecture and key components

✓SageMaker Studio, Studio Lab and Notebook Instances✓Compute options (CPU, GPU, accelerators)✓Domain, users and IAM roles✓Storage: S3, EFS, FSx; security: IAM, VPC, encryption3

Data preparation

✓Importing datasets from S3✓SageMaker Data Wrangler✓Feature engineering and transformation✓Data labeling with Ground Truth and data quality monitoring4

4 and 5. Training, tuning, optimization

✓Built-in algorithms and frameworks✓Estimators, hyperparameters, distributed training✓Spot instances for cost optimization✓Hyperparameter tuning jobs, Debugger and Profiler6

Model deployment

✓Inference concepts: real-time, batch, asynchronous✓Multi-model endpoints and serverless inference✓A/B testing and blue/green deployments✓Auto-scaling, cost optimization and pricing6

7 to 9. MLOps, advanced features, integrations

✓SageMaker Pipelines, CI/CD with GitHub and CodePipeline✓Model registry, automated retraining, drift monitoring✓JumpStart (pre-trained models, LLMs), Canvas, Clarify, Neo✓Lambda, API Gateway, EventBridge, CloudWatch, RDS, DynamoDB, EMR

Support and salient features

Career support and classroom features that come with the course.1

Staffing support

✓Resume preparation✓Mock interview preparation✓Phone interview preparation✓Face to face interview preparation✓Project and technology preparation✓Internship with internal project work✓Externship with client project work2

Our salient features

✓Hands-on labs and homework✓Group discussion and case study✓Course project work✓Regular quiz and exam✓Regular support beyond the classroom✓Students can re-take the class at no cost✓Dedicated conference rooms for group project work✓Live streaming for remote students✓Video recording to catch up on a missed class

Explore more training

See other programs, funding options and the class schedule.All training programs Education grant program Upcoming classes

Ready to start build ML on AWS?

Call 847-350-9034 or book an appointment to talk about this course and funding options.Book an appointment Call 847-350-9034 Education grant program