front matter
I’ve been fortunate to have worked with data and machine learning for about a decade now. My background is in machine learning, and my PhD was focused on applying machine learning in wireless networks. I have published papers (http://mng.bz/zQR6) at leading conferences and journals on the topic of reinforcement learning, convex optimization, and classical machine learning techniques applied to 5G cellular networks.
After completing my PhD, I began working in the industry as a data scientist and machine learning engineer and gained experience deploying complex AI solutions for customers across multiple industries, such as manufacturing, retail, and finance. It was during this time that I realized the importance of interpretable AI and started researching it heavily. I also started to implement and deploy interpretability techniques in real-world scenarios for data scientists, business stakeholders, and experts to get a deeper understanding of machine-learned models.
I wrote a blog post (http://mng.bz/0wnE) on interpretable AI and coming up with a principled approach to building robust, explainable AI systems. The post got a surprisingly large response from data scientists, researchers, and practitioners from a wide range of industries. I also presented on this subject at various AI and machine learning conferences. By putting my content in the public domain and speaking at leading conferences, I learned the following: