Amazon Lex is a service that allows developers to build conversational interfaces for voice and text into applications. With Amazon Lex, the same deep learning technologies that power Amazon Alexa are now available to any developer, so you can quickly and easily build sophisticated, natural language conversational bots (chatbots). Amazon Lex’s advanced deep learning technology provides automatic speech recognition (ASR), for converting speech to text, and natural language understanding (NLU), to recognize the intent of the text so that you can build applications with highly engaging user experience. In this hands-on session, you will build a transactional conversational bot that talks to you using Amazon Polly and Amazon Lex.

Amazon SageMaker is a fully-managed service that enables data scientists and developers to quickly and easily build, train, and deploy machine learning models, at scale. In this hands-on session, you will spin up a zero-setup Jupyter notebook environment for data exploration and preparation and explore features of Amazon SageMaker including a one-click distributed training environment, highly-optimized machine learning algorithms with built-in model tuning, and deployment without engineering effort. You will use one of the built-in algorithms to train your model, deploy it to a managed endpoint and evaluate your predictions.

Amazon Rekognition, a deep learning-based service, makes it easy to add image and video analysis to your applications. In this hands-on session, you will develop a solution that will stream and analyze social media images using Amazon Rekognition features. The solution will entail a repeatable and automated process that follows best practices for architecting in the cloud, such as designing for high availability and scalability.

Apache Spark has been a framework of choice for many years to address challenges for complex analysis of data. In this hands-on session, you will gain a deep understanding of Apache Spark and SageMaker integration and learn how to use the SageMaker-Spark SDK in a notebook instance. You will focus on using Apache Spark for pre-processing data and Amazon SageMaker for model training and hosting.