An introduction to Deep Learning in Azure
2022TL; DR
In this session we will look at the basics of Deep Learning. What is it, why is it deep, what problems does is solve, how do you get started and more.
Session Details
In this session we will take a gentle introduction to Deep Learning.
If you have attended a session or read a book on machine learning that did not mention Deep Learning, AI or Neural Networks then it was most likely a shallow machine learning session.
Shallow machine learning is fantastic when you need to have accountability and auditing of your machine learning models. It is great for a lot of problems, but it does require a lot of work up front. That work is feature engineering. Deep Learning is not a silver bullet by any means, but it is quite different to shallow learning and does not require the same degree of feature engineering. Neural nets, the magic behind deep learning can be shaped to work for all sorts of problems, text generation, image processing, dynamic generation, you name it, there is a neural network trying to solve it.
In this session we will look at the basics of Deep Learning. What is it, why is it deep, what problems does is solve, how do you get started and more. There is an assumption that you know a bit about machine learning, but you will still enjoy the session even if this is your first exposure to machine learning.
3 things you'll get out of this session
Speakers
Terry McCann's previous sessions
Docker & Kubernetes for the Data Scientist
Deployment == Return on investment. This session looks to show you how to do that for Machine Learning.
Machine Learning in Azure Synapse
There is a lot of content available on Synapse for Data Engineering, but what about Machine Learning? In this session we will look at how to integrate a SparkML model in Synapse.
Rapid Requirements: Introducing the Machine Learning Canvas
In this session, we will introduce the Advancing Analytics Machine Learning Canvas and how it can be used to capture requirements for Machine Learning Projects.
Machine Learning in Azure Databricks
In this session we focus on how Spark implements Machine Learning at Scale with Spark ML.
Deploy ML models faster with Data Science DevOps
In this session I will show you how to apply DevOps practices to speed up your development cycle and ensure that you have robust deployable models. We will focus on the Azure cloud platform in particular, however this is applicable to other platforms
Enhancing relational models with graph in SQL Server 2017
This session explores SQL Server 2017's Graph processing to better understand interconnectivity and behaviour in your data.