In this course we will cover the major steps in a data science project. From data access, data pre-processing, and data visualization, to machine learning, model optimization, and deployment using KNIME Analytics Platform.

What do product name generation and neural machine translation have in common?

Both involve sequence analysis which can be implemented via recurrent neural networks (RNN) with LSTM layers.

LSTM Neural Networks are the state of the art technique for sequence analysis. In this presentation, we find out what LSTM layers are, learn about bidirectional and stacked LSTM and the difference between many-to-one, many-to-many, and one-to many-structures, and train many-to-many LSTM networks for both use cases.

In recent years, a wealth of tools has appeared that automate the machine learning cycle inside a black box. We take a different stance. Automation should not result in black boxes, hiding the interesting pieces from everyone. Modern data science should allow automation and interaction to be combined flexibly into a more transparent solution.

In some specific cases, if the analysis scenario is well defined, then full automation might make sense. However, more often than not, these scenarios are not that well defined and not that easy to control. In these cases, a certain amount of interaction with the user is highly desirable.

By mixing and matching interaction with automation, we can use Guided Analytics to develop predictive models on the fly. More interestingly, by leveraging automated machine learning and interactive dashboard components, custom Guided Analytics Applications, tailored to your business needs, can be created in a few minutes.

We'll build an application for automated machine learning using KNIME Software. It will have an input user interface to control the settings for data preparation, model training (e.g. using deep learning, random forest, etc.), hyperparameter optimization, and feature engineering. We'll also create an interactive dashboard to visualize the results with model interpretability techniques. At the conclusion of the workshop, the application will be deployed and run from a web browser.

In this course we cover the major steps in a data science project, from data access, data pre-processing, and data visualization to machine learning, model optimization, and deployment using the KNIME Analytics Platform.

Do you want to know what your customers, users, contacts, or relatives really think? Find out by building your own sentiment analysis application.

In this workshop you will build a sentiment analysis application, step by step, using KNIME Analytics Platform. After an introduction to the most common techniques used for sentiment analysis and text mining, we will work in three groups, each one focusing on a different technique.

• Deep Learning: This group will work with the visual Keras deep learning integration available in KNIME (completely code free)
• Machine Learning: This group will use other machine learning techniques, based on native KNIME nodes
• Lexicon Based: This group will focus on a lexicon based approach for sentiment analysis