KNIME Spring Summit 2023

TRAINING 1: 10:00AM - 5:30PM

TRAINING 2: 10:00AM - 5:30PM

TRAINING 3 10:00AM - 5:30PM

You have developed a nice data app with KNIME Analytics Platform. What are the next steps to productionize it? In this course we will show you what to do to get your data app up and running, including: testing, deployment on KNIME Business Hub, permissions & versioning, custom styling, orchestration, and more.

The course includes sentiment analysis workflows that can be used over any type of text, and a “what country has this flag?” game that is implemented as a data app. Besides learning about data apps in KNIME, you will have multiple workflows that can be adapted to your needs by the end of the course. 

In the first session of this course, you will learn what needs to be checked before deploying a data app on KNIME Business Hub. In the second session, you will be introduced to KNIME Business Hub — including how to upload workflows and deploy them as data apps or workflow schedules. Next, in the third session, you will learn how to create interactive data apps that can be deployed on KNIME Business Hub and made available as web browser applications. Finally, in the fourth session, you will learn about runtime optimization, workflow orchestration, and general best practices. We wrap up in a fifth session with exercise solutions. 

At the end of each session, we will provide some practical exercises to test and apply your knowledge.

TRAINING 4: 10:00AM - 5:30PM

This course focuses on how to use KNIME Analytics Platform for data engineering and how to apply best practices when building data processing pipelines.

Learn the concepts behind connecting to multiple data sources, the methods for data anonymization, and advanced database topics. Be introduced to the Apache Hadoop ecosystem and find out how to handle big data with the Apache Spark integration. Finally, learn how to build and orchestrate modular workflows.

Put your knowledge into practice with hands-on exercises to build and orchestrate two applications: first, extract, validate, transform, blend, anonymize, and load the customer data to a database; second, use Spark to access, impute missing values, and aggregate the website usage data. 

This is an in-person instructor-led course run by our KNIME data scientists. 

What level of KNIME experience is needed for this course?
This course doesn’t provide a detailed introduction to KNIME Analytics Platform. You should be competent in using KNIME Analytics Platform. We expect that you have already built KNIME workflows and are aware of the workflow control concepts such as flow variables, loops, switches, and error handling. We recommend taking this course after obtaining the L1 and L2 KNIME proficiency or equivalent.

TRAINING 5: 10:00AM - 5:30PM

Some of the common topics on data extraction today include how to extract from exotic sources like websites and how to use REST services. Once the data is extracted, what is the best way to visualize that data in order to pitch or sell an idea? To answer this question, it is best to arm yourself with a small collection of low code data extraction and visualization tools.

In this course, we offer the chance to learn more about advanced data extraction techniques and advanced visualization including dashboards. We introduce a useful low code tool for data extraction as well as various visualizations. We begin the course with the basics of creating simple dashboards, and conclude with interactive and refined user interfaces. In addition, we also demonstrate how to extract text data from various sources using Regex. 

This is an in-person instructor-led course run by our KNIME data scientists. 

What level of KNIME experience is needed for this course?
This course doesn’t provide a detailed introduction to KNIME Analytics Platform. You should be competent in using KNIME Analytics Platform. We expect that you have already built KNIME workflows and are familiar with concepts and techniques for data wrangling. We recommend taking this course after obtaining the L1 and L2 KNIME proficiency or equivalent.

TRAINING 6: 10:00AM - 5:30PM

This course introduces you to the most commonly used machine learning algorithms used in data science applications. 

We will explore different supervised learning algorithms for classification and numerical problems such as decision trees, logistic regression, and ensemble models. In addition, we will introduce techniques such as neural networks and deep learning. We will also examine unsupervised learning techniques, such as recommendation engines, as well as various clustering methods including k-means, hierarchical clustering, and DBSCAN. 

We will also discuss various evaluation metrics for trained models, and showcase a number of classic data preparation techniques, such as normalization and dimensionality reduction.

This is an in-person instructor-led course designed for current and aspiring data scientists eager to learn more about machine learning algorithms used commonly in data science projects.

What level of KNIME experience is needed for this course?
You must be competent in using KNIME Analytics Platform. We strongly recommend you be at the level of an advanced KNIME user -  for example you’ve taken a basic and advanced KNIME Analytics Platform Course and/or use KNIME on a regular basis.