Summary
In this chapter, we explored how we can use deep learning for both tabular and time series data. Instead of building the neural networks from scratch, we used modern Python libraries which handled most of the heavy lifting for us.
As we have already mentioned, deep learning is a rapidly developing field with new neural network architectures being published daily. Hence, it is difficult to scratch even just the tip of the iceberg in a single chapter. That is why we will now point you toward some of the popular and influential approaches/libraries that you might want to explore on your own.
Tabular data
Below we list some relevant papers and Python libraries that will definitely be good starting points for further exploration of the topic of using deep learning with tabular data.
Further reading:
- Huang, X., Khetan, A., Cvitkovic, M., & Karnin, Z. 2020. Tabtransformer: Tabular data modeling using contextual embeddings. arXiv preprint arXiv:2012...