Do you know?

This is the best time to learn machine learning as the trends in the market suggest. The global machine learning market is estimated at US dollar 8.43 billion in 2019 and is expected to reach 117 billion by 2027, at a CAGR of 39.2%. Thus, job opportunities in this sector are going to grow with a boom in the coming years.

AI and machine learning are not only used in machine learning applications but also in the Internet of things, like self-driving cars, smart homes, digital assistants, etc. In fact, during COVID-19, statistical machine learning played a significant role in generating advanced models for predicting virus spread, and aided in the management of the pandemic across the world. Machine learning in finance has also secured a respectable place among business leaders using the technology for generating automatic models for stock management.

Program Curriculum

Module 2: Data Engineering in AWS

• Data Engineering in AWS
  • introduction to Data Engineering
  • Amazon S3
  • Amazon S3 - Storage Classes & Lifecycle Rules
  • S3 Security
  • Amazon S3 Security
  • Glue Data Catalog & Crawlers
  • Glue ETL
  • Kinesis Data Streams & Kinesis Data Firehose
  • Kinesis Data Analytics
  • Kinesis Video Streams
  • Kinesis ML Summary
  • introduction to Athena
  • AWS Data Stores in Machine Learning
  • AWS Data Pipelines
  • AWS Batch
  • AWS DMS - Database Migration Services
  • AWS Step Functions
  • Full Data Engineering Pipelines
  • AWS Containers
  • AWS Serverless

Module 3: Data Analysis in AWS

• Data Engineering in AWS
  • Introduction Data Analysis
  • Preparing Data for Machine Learning in a Jupyter Notebook.
  • Time Series-Trends and Seasonality
  • Amazon Athena
  • Overview of Amazon Quicksight
  • Types of Visualizations, and When to Use Them.
  • Hadoop Overview & Elastic MapReduce (EMR)
  • Apache Spark on EMR
  • EMR Notebooks, Security, and Instance Types

Module 4: Modeling in AWS

• Modeling in AWS
  • Introduction to Modeling
  • Introduction to Deep Learning
  • Activation Functions
  • Convolutional Neural Networks
  • Recurrent Neural Networks
  • Deep Learning on EC2 and EMR
  • Tuning Neural Networks
  • Regularization Techniques for Neural Networks (Dropout, Early Stopping)
  • Grief with Gradients: The Vanishing Gradient problem
  • L1 and L2 Regularization
  • The Confusion Matrix
  • Precision, Recall, F1, AUC, and more
  • Ensemble Methods (Bagging and Boosting)

Module 5: Artificial Intelligence in AWS

• Artificial Intelligence in AWS
  • Amazon Augmented AI
  • Amazon CodeGuru
  • Amazon Comprehend
  • Amazon Forecast
  • Amazon Fraud Detector
  • Amazon Kendra
  • Amazon Lex
  • Amazon Personalize
  • Amazon Polly
  • Amazon Rekognition
  • Amazon Textract
  • Amazon Transcribe
  • Amazon Translate
  • AWS DeepComposer
  • AWS DeepLens
  • AWS DeepRacer
  • AWS Panorama
  • Amazon Monitron
  • Amazon HealthLake
  • Amazon Lookout for Vision
  • Amazon Lookout for Equipment
  • Amazon Lookout for Metrics

Module 6:Machine Learning in Amazon SageMaker

• Introduction to SageMaker
  • Understanding Machine Learning Pipeline
  • Why SageMaker ?
  • SageMaker for Machine Learning
• SageMaker Setup
  • AWS S3 bucket creation
  • Notebook creation
  • Data collection, transformation & upload to S3
  • Model Selection & Training
  • Model Deployment
  • Model Validation
• ​​​​​​​SageMaker Built-in Algorithms
  • Blazing Text
  • DeepAR Forecasting
  • Factorization Machines
  • Image Classification Algorithm
  • IP Insights
  • K-Means Algorithm
  • K-Nearest Neighbors (k-NN) Algorithm
  • Latent Dirichlet Allocation (LDA)
  • Linear learner algorithm
  • Neural Topic Model (NTM) Algorithm
  • Object2Vec
  • Object Detection Algorithm
  • Principal Component Analysis (PCA) Algorithm
  • Random Cut Forest (RCF) Algorithm
  • Semantic Segmentation
  • Sequence to Sequence (seq2seq)
  • XGBoost Algorithm
• ​​​​​​​Model Training & Tuning
  • Monitor & Analyze Training jobs
  • Incremental Training
  • Hyperparameter Tuning
• ​​​​​​​Model Deployment
  • Interface Pipeline
  • Train once & Run Anywhere using Neo
  • Elastic Interface
  • Automatic Scaling
  • Standard Practices
• ​​​​​​​Using Machine Learning Frameworks with SageMaker
  • Apache Spark with Amazon SageMaker
  • TensorFlow with Amazon SageMaker
  • Apache MXNet with Amazon SageMaker
  • Scikit-learn with Amazon SageMaker
  • PyTorch with Amazon SageMaker
• ​​​​​​​Ground Truth using SageMaker
  • Data Labelling
  • input & Output data to Ground Truth
  • Workforce for labelling - public, private, vendor

Module 7: Machine Learning Operations(MLOps)

• MLOps
  • What is MLOps?
  • MLOps Motivation: High-level view
  • MLOps challenges
  • MLOps challenges similar to DevOps
  • Automated ML pipelines vs CI/CD ML pipelines
  • Amazon SageMaker Pipelines
  • AWS SageMaker studio

Module 8:Monitoring & Watching

• Monitoring & Watching
  • Monitoring with CloudWatch
  • Logging with CloudWatch
  • Logging in SageMaker API Calls with AWS CloudTrail
• Using SageMaker SDK
  • Understanding boto3
  • Actions - Common APIs
  • Understanding SageMaker Endpoint API

Syllabus

What you’ll learn

Reviews and Testimonials