With the growing popularity of single-cell RNA-Seq analysis, the t-SNE projection of multi-dimensional data is appearing more often in publications and online. If you’ve ever wanted to develop a better intuitive feel for what exactly t-SNE does and where it can go wrong, this interactive tutorial (by Martin Wattenberg and Fernanda Viegas) is extremely compelling and useful.
In addition to providing a wonderful, interactive plotting function, the authors go on to provide an informative tutorial explains the pitfalls and challenges of the optimization and hyper-parameter tuning of t-SNE projections and how to get the most from the plots. Here is an example:
In the example above, tuning the “perplexity” of the t-SNE projection causes the correct reconstruction of the data when values are between 30-50, but the same method fails when the parameter falls outside those ranges (i.e., too small or too large).
Go check out this distill.pub site. It’s worth your time.
Here are five different ways to gain an introduction to the topic of CNNs. Each approach is geared toward a different style of learning:
Visualize them in real time with your own inputs (this is amazing!)
Watch a lecture by the “godfather” of neural nets, Geoff Hinton.
Take a top-ranked online course on Deep Learning.
Learn the math behind them.