Topic Thread

Learning to Leverage AutoAI to Increase your Productivity

  • 1.  Learning to Leverage AutoAI to Increase your Productivity

    Posted Fri August 21, 2020 04:09 PM

    IBM just announced the course Machine Learning Rapid Prototyping with IBM Watson Studio on Coursera. As the lead curriculum developer, I would like to share with you some of the highlights and how I think you can benefit the most from taking this course. This course is ideal for data scientists who have too many projects on their plate and need to save time. Like having your own data science assistant, Watson Studio AutoAI Experiments can automate some of your workflow, leaving you to focus on using your expertise for higher-level data science tasks. The course explains how the Watson Studio AutoAI Experiments tool can be used to build an optimized Python-language machine learning model for a use case in mere minutes.  

     

    In the course, you'll learn the technologies underlying the AutoAI Experiments tool in order to understand the strengths of automation in the Data Science workflow. Given an understanding of how the tool works, you'll be able to interpret the results of AutoAI in the context of your domain knowledge. This is a hands-on course which will follow several use cases to evaluate the prototypes generated by the AutoAI tool. These prototypes take the form of a Python notebook, making the results of the automation transparent and permitting you to make manual adjustments to the prototype.  

     

    This course will take you through each step in the Data Science workflow including data preparation, model selection, feature engineering and hyperparameter optimization. You'll learn the algorithms developed by IBM research scientists which underlie automation at each step in the workflow. For each step, including data preparation, model selection, feature engineering and hyperparameter optimization, you'll examine the AutoAI performance across several use cases. 

     

    After taking this course, you'll be able to incorporate AutoAI into your project work, improving your productivity by automating some of the manual trial and error work of data science in areas like data preparation, model selection, feature engineering and hyperparameter optimization. Understanding the capabilities of AutoAI and how it can best augment your skills as a data scientist will allow you to go from use case to prototype much faster. Learning about AutoAI will also equip you for a future in the field of Data Science in which more automated tools for AI are expected to become available.  



    ------------------------------
    Meredith Mante
    ------------------------------