Recently I came across this incredible survey paper on the use of neural networks for tabular data. After going through it carefully, I can confidently say that it's thus far THE best paper on the subject. It goes into depth of all the main issues that have stymied the use of NNs in this domain. The paper is very thoughtful, systematic, and fairly thorough. Despite what the authors claim, though, it is not the first paper on the topic, but it goes well beyond many recent papers on the subjects. It also doesn't have as an exhaustive set of datasets that it uses as some of the other papers.

Bojan is a Machine Learning Modeler at NVIDIA. He has been working in Machine Learning and Data Science fields for seven years and has experience with real-world FinTech problems. He is a Quadruple Kaggle Grandmaster and is the first person to be ranked in the top 10 in all four Kaggle categories simultaneously. My interests have somewhat evolved over the years. For a while, I was really interested in NLP problems, but that field has become very hard to keep pace with.

The Dogs versus Cats Redux: Kernels Edition playground competition revived one of our favorite "for fun" image classification challenges from 2013, Dogs versus Cats. This time Kaggle brought Kernels, the best way to share and learn from code, to the table while competitors tackled the problem with a refreshed arsenal including TensorFlow and a few years of deep learning advancements. In this winner's interview, Kaggler Bojan Tunguz shares his 4th place approach based on deep convolutional neural networks and model blending. I am a Theoretical Physicist by training, and have worked in Academia for many years. A few years ago I came across some really cool online machine learning courses, and fell in love with that field.