Summit

KNIME Spring Summit

- - Online
KNIME Spring Summit 2020 Online

We would have loved to have met everyone in Berlin but unfortunately that isn’t possible this year. We’ve therefore done our best to move the Summit online and have just published a revised program. Despite this situation, we’re really looking forward to connecting all those home offices out there and creating a special summit spirit together with the KNIME community.

 

Overview

Starting with a week of courses and talks, our digital summit format will continue throughout the month of April with presentations by KNIME customers and users, as well as workshops.

Sign up for the latest program information

 

The Virtual KNIME Summit

Welcome to our virtual conference room. The following KNIME talks, including the keynote presentation by Dean Abbott, will be run as a free webinar for everyone to attend1.

Wednesday, April 1, 3:00 PM - 6:00 PM (CEST) - Berlin.

  • The Future of Data Science: Integrated Deployment by Michael Berthold
  • KNIME: An Introduction by Cynthia Padilla
  • Community, Partners, and Teaching: the KNIME Family by Rosaria Silipo and Paul Treichler
  • What's New and Cooking in KNIME Analytics Platform by Bernd Wiswedel
  • What's New and Cooking in KNIME Server by Jim Falgout
  • Keynote Presentation by Dean Abbott (Smarter HQ)

 

Talk to the KNIMErs: Q&A Sessions

The following sessions will be run as a free webinar for everyone to attend1. Detailed program will be announced soon!

Thursday, April 2, 3:00 PM - 6:00 PM (CEST) - Berlin.

  • KNIME Workflow Doctor
  • Developer Session

 

KNIME Courses in the Online Classroom

Our virtual classroom doors open on March 30. Courses are split into four one-hour sessions. In between these sessions you'll have time to work on some exercises - during which we'll be available to answer questions and help you. At the end of each break, we'll present the solution workflow2.

Monday, March 30:

[L1-DS] KNIME Analytics Platform for Data Scientists: Basics

Time (Europe class): 9:30 AM - 5:15 PM (CEST) - Berlin (a few new spaces have opened up - get in fast!)

Time (Americas class): 11:30 AM - 7:15 PM (EDT) - New York

New time offering: Monday, April 6: 9:30 AM - 5:15 PM (CEST) - Berlin. Access to this course is via a dedicated ticket, when you register.

Designed for those who are just getting started on their data science journey with KNIME Analytics Platform. The course starts with a detailed introduction of KNIME Analytics Platform - from downloading it through to navigating the workbench. It then introduces you to KNIME Analytics Platform covering the whole data science cycle from data import, manipulation, aggregation, visualization, model training, and deployment. Learn how to export your data and create a report for sending to your colleagues. View (CEST) agenda. View (EDT) agenda.

[L1-DW] KNIME Analytics Platform for Data Wranglers: Basics

Time: 9:30 AM - 5:15 PM (CEST) - Berlin (a few new spaces have opened up - get in fast!)

Designed for those who are just getting started on their data wrangler journey with KNIME Analytics Platform. The course starts with a detailed introduction of KNIME Analytics Platform. It focuses on accessing, merging, transforming, fixing, standardizing, and inspecting data from different sources. It dives into data cleaning and aggregation, using methods such as advanced filtering, concatenating, joining, pivoting, and grouping. View agenda.

[L4-BD] Introduction to Big Data with KNIME Analytics Platform

Time: 9:30 AM - 5:15 PM (CEST) - Berlin.

Focuses on how to use KNIME Analytics Platform for in-database processing, predicting values with KNIME, and writing/loading data into a database. Get an introduction to the Apache Hadoop ecosystem and learn how to write/load data into Hadoop. Learn about the KNIME Spark Executor, preprocessing with Spark, machine learning with Spark, and how to export data back into KNIME/Hadoop. View agenda.

 

Tuesday, March 31:

[L2-DS] KNIME Analytics Platform for Data Scientists: Advanced

Time (Europe class): 9:30 AM - 5:15 PM (CEST) - Berlin (a few new spaces have opened up - get in fast!)

Time (Americas class): 11:30 AM - 7:15 PM (EDT) - New York

New time offering: Tuesday, April 7: 9:30 AM - 5:15 PM (CEST) - Berlin. Access to this course is via a dedicated ticket, when you register.

Builds on the KNIME Analytics Platform for Data Scientists: Basics by introducing advanced data science concepts. Learn all about flow variables, different workflow controls such as loops, switches, and error handling. Explore advanced data mining techniques and learn how to create models in KNIME Analytics Platform. View (CEST) agenda. View EDT agenda.

[L2-DW] KNIME Analytics Platform for Data Wranglers: Advanced

Time: 9:30 AM - 5:15 PM (CEST) - Berlin (a few new spaces have opened up - get in fast!)

Builds on the KNIME Analytics Platform Course for Data Wranglers: Basics by introducing advanced concepts for building and automating workflows.  Learn all about flow variables, different workflow controls such as loops, switches, and how to catch errors. And lastly learn how to visualize your data and look beyond data wrangling towards data science, training your first classification model. View agenda.

[L3-PC] KNIME Server Course: Productionizing and Collaboration

Time: 9:30 AM - 5:15 PM (CEST) - Berlin.

Dives into the details of the commercial KNIME Server and KNIME WebPortal - discussing them from three different points of view: the power user, the administrator, and the end user. All tools and features designed for each one of these three personas are shown in detail. Find out how to exchange workflows and data between the server and the client, how to take advantage of the many server dedicated nodes and features when implementing a workflow, how to set access rights on workflows, data, and metanodes, share metanodes, execute workflows remotely and from the KNIME WebPortal, how to schedule report and workflow executions, and more. View agenda.

 

Thursday & Friday, April 2 & 3:

The following courses are run over two half days in order to compensate for both the EU and US time zones.

[L4-ML] Introduction to Machine Learning Algorithms

To cater for high demand, this course will be starting at the following times on both April 2 and April 3. Select which time you'd like to join when you register.

9:00 AM - 1:00 PM CEST - Berlin.

3:00 PM - 7:00 PM CEST - Berlin (9:00 AM - 1:00 PM EDT - New York).

Introduces you to the most commonly used machine learning algorithms in data science applications. This course will explore different supervised algorithms for classification and numerical problems such as decision trees, logistic regression, and ensemble models. We'll also look at recommendation engines and neural networks and investigate the latest advances in deep learning. In addition, we'll examine unsupervised learning techniques, such as clustering with k-means, hierarchical clustering, and DBSCAN. We'll also discuss various evaluation metrics for trained models and a number of classic data preparation techniques, such as normalization or dimensionality reduction. View (9AM) agenda. View (3PM) agenda

[L3-PC] KNIME Server Course: Productionizing and Collaboration

This course is being offered at the following time:

Time: 3:00 PM - 7:00 PM CEST - Berlin (9:00 AM - 1:00 PM EDT - New York).

Dives into the details of the commercial KNIME Server and KNIME WebPortal - discussing them from three different points of view: the power user, the administrator, and the end user. All tools and features designed for each one of these three personas are shown in detail. Find out how to exchange workflows and data between the server and the client, how to take advantage of the many server dedicated nodes and features when implementing a workflow, how to set access rights on workflows, data, and metanodes, share metanodes, execute workflows remotely and from the KNIME WebPortal, how to schedule report and workflow executions, and more. View agenda.

Register now

 

Keep Connected: Online Learning in April

We want to keep you, the community, connected throughout the month of April. Dial in to see presentations given by our summit speakers and take part in virtual workshops. Sign up here to be notified as soon as dates are released.

User Presentations

Speakers invited to the on-site summit are hosting webinars during the month of April. At the end of each presentation your questions can be put to the speaker. Stay tuned to find out more: dates and times of these webinars, plus how to register will be posted here. Confirmed talks so far:

  • Conformal Prediction: Enhanced Method for Understanding the Prediction Quality. Artem Ryasik (Redfield)
  • Automatically Detecting Data Science Pitfalls in KNIME using KNIME. Gopi Krishnan Rajbahadur (Queen's University)
  • Bringing Data Manipulation from KNIME into TIBCO Spotfire. Maxime Guitet, Lionel Colliandre (Discngine)
  • Use of KNIME to Automate Data Transfer from Sharepoint to PerkinElmer Inventory. Fabio Rancati (Chiesi Farmaceutici)

Workshops

A selection of the workshops scheduled for the on-site summit will be run as webinars. Our online tutors have hands-on exercises that get discussed at the end of each webinar. Stay tuned to find out more: dates and times of these webinars, plus how to register will be posted here.

Time Series Analysis Workshop - Corey Weisinger, Maarit Widmann (KNIME)

At this workshop, you’ll learn about the the main concepts behind Time Series and IoT, before splitting into groups to build the following applications: 

  • Group 1: Visual analytics of time series
  • Group 2: Forecasting with machine learning based models
  • Group 3: Forecasting with ARIMA models

We’ll provide a real-world IoT dataset, jump-start workflows, and final solutions for the proposed tasks. The workflows are built using the set of time series components provided in KNIME for preprocessing, transforming, aggregating, forecasting, and inspecting time series.

Behind the Scenes of Machine Learning - Kathrin Melcher, Rosaria Silipo (KNIME)

Do you know the difference between supervised and unsupervised learning? And do you know how a recommendation engine works? Do you know what the algorithm is behind the random forest? We’ll begin by exploring the differences between supervised and unsupervised algorithms and their use cases. Next, we’ll focus on classification problems, taking a look behind the decision tree algorithm, ensembles of it (e.g. random forest), and how to evaluate the models. The last part of the workshop covers a number of unsupervised algorithms with a focus on clustering algorithms and recommendation engines.

Working with the RDKit in KNIME Analytics Platform - Daria Goldmann, Greg Landrum (KNIME)

In this hands-on workshop we'll work through a couple of examples of common cheminformatics use cases selected to give a broad overview of both what you can do with KNIME and what's possible with the RDKit. In addition to using the RDKit KNIME nodes, we'll also provide examples of how you can use the broader functionality available using Python and Java scripting nodes available in KNIME. In this workshop you won't just learn new stuff, you'll also walk out with a couple of useful workflows that you can continue to adapt and use.

Text Mining on Biomedical Literature - Today: Topic Modeling - Martyna Pawletta (KNIME)

This hands-on workshop will teach you how to build a workflow using text mining methods. We’ll implement a topic modeling approach using documents from biomedical literature related to user-selected diseases of interest. We’ll start by automatically extracting text documents and perform topic modeling using the Latent Dirichlet Allocation (LDA) method. To conclude, you’ll learn how to create interactive visualizations of the extracted documents and topics. We’ll provide the data and an example workflow with some small hands-on exercises. Prior knowledge about KNIME is not required, but you do need to bring your own laptop preinstalled with the latest version of KNIME Analytics Platform and the Text Mining extension.

Deep Learning for Image Analysis  - David Kolb, Benjamin Wilhelm (KNIME)

Deep learning - the utilization of many-layered neural networks - now enables computers to make sense of data that have previously been too complex. An example of such are images, where deep learning based approaches achieve excellent results on many tasks. After a brief introduction to image based deep learning (Convolutional Neural Networks), we’ll show you how to build and apply basic Image Analysis deep learning models in KNIME. Here, you’ll learn about tasks such as classification and segmentation, and we’ll look at an additional, more advanced use case. 

KNIME Text Mining with NER Modeling & Deep Learning - Julian Bunzel (KNIME)

In the digital era where the majority of information is made up of text-based data, text mining plays an important role for extracting useful information, providing patterns and insight from an otherwise unstructured data. In this workshop, you'll learn how to train your own, customized named entity recognition model. You’ll find out how to apply it to extract entities from text, and create entity relation networks.

Sharing & Deploying Data Science with KNIME Server - Roland Burger, Marten Pfannenschmidt (KNIME)

You’re currently using the open source KNIME Analytics Platform but want to work across teams and business units? KNIME Server is the enterprise software for team-based collaboration, automation, management, and deployment of data science workflows. Non-experts are given access to data science via KNIME Server and WebPortal, or can use REST APIs to integrate workflows as analytics services into applications. At this workshop, we’ll introduce you to KNIME Server capabilities and cover everything you need to manage your analytics at scale - deploying your workflows for sharing and collaboration, scheduling and automating tasks, templating and version control. We’ll demonstrate the power of the REST API of KNIME Server and WebPortal - the ideal way for bringing data analytics to your business users.

Guided Labeling: Human-in-the-Loop Label Generation with Active Learning & Weak Supervision - Paolo Tamagnini, Adrian Nembach (KNIME)

We’re in the age of data. In recent years, many companies have already started collecting large amounts of data about their business. Other companies are starting now. However, before you can train any decent supervised model you need ground truth data. Before you can proceed, you need a sufficiently large set of correctly labeled data records to describe your problem. And data labeling - especially in a sufficiently large amount - is expensive. In this workshop you’ll learn about the main concepts of the Guided Labeling procedure based on Active Learning and Weak Supervision KNIME Extensions. We’ll also show example workflows from the KNIME Hub and blueprint web-applications via the KNIME WebPortal to interactively label any document set while investing only a fractional amount of time in manual labeling and insertion of rules.

Building a Drug Discovery Workflow in 8+1 steps with KNIME - Dora Barna, Norbert Sas (ChemAxon)

This workshop will focus on how cheminformatics tools can be used in chemical research and development related use cases. Following a brief introduction of how ChemAxon tools can be used in the KNIME Analytics Platform, we’ll build a workflow that is typically used in early phase drug discovery projects. During the workshop you’ll learn how clustering, library enumeration, property prediction, fast chemical structure search, and model building can be used together in KNIME. By the end of the workshop we’ll generate an extended collection of compounds that are easily accessible within the desirable chemical property space and that can be used as starting points in a quest for new bioactive compounds.

KNIME Big Data Workshop - Björn Lohrmann (KNIME)

At this workshop you’ll learn how to perform data wrangling and advanced analytics on big data with the KNIME Big Data Extensions. We’ll show you how to do in-database processing on Apache Hive/Impala, perform advanced analytics with Apache Spark (either locally or on Cloudera, Databricks, ...) and to how to run KNIME workflows directly on Spark.

GDPR Compliance through Advanced Anonymization Techniques - Artem Ryasik, Jan Lindquist (Redfield)

Lack of proper anonymization or pseudonymization introduces risks; if there is a data breach, huge penalties are applied for non-compliance with GDPR. Even if you think you’ve analyzed your data and believe it to be anonymized, there are assessment techniques that can measure the risks. In this workshop you’ll learn how to work with the new Privacy Extension for KNIME, which utilizes advanced anonymization techniques.

 

Subscribe to Summit Updates

 

Upon clicking "Subscribe" you'll automatically be added to our dedicated email list for regular program updates.

* indicates required

 


1 You'll receive the link to your chosen session(s) one day prior to it starting.

2 Registered already for the in-person summit? You can attend any of the online courses listed above free of charge. You should have received a promo code via email. Signing up for the first time? Courses are available at a special price of  EUR 50 / apx. USD 55 (exl. VAT) per course. NOTE: You'll receive the link to your chosen course(s) one day prior to it starting. We'll be using Zoom - so please make sure you have a stable internet connection.