Is deep learning a silver bullet? – Black box & explainability
Deep learning is often seen as the silver bullet of machine learning methods. However, as a data scientist, I know that it has at least one big crux. In “Torch”, our new data science series, I will show you how deep learning differs from more traditional machine learning and what challenges you have to face if you want to use it.
What the biggest crux of this powerful machine learning method is.
Which concrete questions you have to be able to answer when implementing a deep learning solution.
Want to see this on a real-life example? In my takeaway, I show you how my team and I implemented an anomaly detection model based on deep learning and give you specific tips for your own deep learning use case.
Hello, my name is Saeid, and I am a data scientist at Trivadis – Part of Accenture. My fascination with data mining and machine learning methods and especially their business application led me to a master’s degree with the focus on data analysis and business intelligence. Having worked on many data science projects, I have developed extensive expertise in the field. I like to keep up to date with the latest technological innovations and constantly educate myself. In my free time, I enjoy doing different sports and hanging out with my friends. Also, I never say no to an opportunity to go on a vacation! PS: Did you enjoy my “Torch” episode? Then let’s get in touch – I would love to pass the torch and discuss the world of data science further!
What I share with you
Despite its cruxes, deep learning is well suited for some use cases. Like the solution my team and I implemented for an automotive manufacturer. Why we decided to use deep learning and how we dealt with the challenges it presented? In my takeaway, you will find concrete tips on how to determine whether a deep learning model fits your specific use case and how to implement it successfully.
