This half day (4 hours) hands-on bootcamp is for developers of all skill level to come together to learn deep learning on NLP using Tensorflow with Amazon Sagemaker.
Get free deep learning training. Together we will work through several deep learning labs, build an end-to-end AI/ML pipeline for natural language processing with Amazon SageMaker. You will get hands-on experience with the deep learning, NLP, BERT, Tensorflow and Sagemaker.
Every attendee will receive a free AWS instance for this bootcamp

---

Agenda:

• [30 mins] Welcome, Introductions, and Demo Setup
• [30 mins] Ingest and Explore Data
• [30 mins] Analyze Data for Bias
• [30 mins] BERT Feature Engineering
• [15 mins] Q&A / Break
• [30 mins] BERT Fine-Tuning
• [30 mins] Build an End-to-End BERT Text Classifier Pipeline
• [30 mins] Analyze Model for Bias and Explainability
• [15 mins] Register and Deploy Model
• [15 mins] Q&A / Wrap Up

Attendees will learn how to:

• Ingest data into S3 using Amazon Athena and the Parquet data format
• Visualize data with pandas and matplotlib on SageMaker notebooks
• Run data bias analysis with SageMaker Clarify
• Perform feature engineering on a raw dataset using Scikit-Learn and SageMaker Processing Jobs
• Store and share features using SageMaker Feature Store
• Train a custom BERT model using TensorFlow, Keras, and SageMaker Training Jobs
• Evaluate the model using SageMaker Processing Jobs
• Track model artifacts using Amazon SageMaker ML Lineage Tracking
• Run model bias and explainability analysis with SageMaker Clarify
• Register and version models using SageMaker Model Registry
• Deploy a model to a REST Inference Endpoint using SageMaker Endpoints
• Automate ML workflow steps by building end-to-end model pipelines using SageMaker Pipelines

Modern browser - and that is it!
Nothing will be installed on your local laptop

Data scientists and machine learning practitioners with a working knowledge of machine learning algorithms and concepts, who are proficient in Python programming at an intermediate level, and who are familiar with Jupyter notebooks and statistics.