Topological Data Analysis for Machine Learning Lecture II: Computational Topology

In which we discuss a multi-scale variant of simplicial homology, viz. persistent homology, provide copious examples, and show that everything—once again—boils down to neat linear algebra calculations.

(this video is part of a lecture at ECML PKDD 2020, the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases)

[masonholcombe]

These are really some well put together lectures. You do a great job at taking this "abstract nonsense" and reformatting it in a way that is discernible and elegant! Thanks!

[jinyunghong]

Thank you so much for the great lecture series. I'm a newbie for topological data analysis but this series is really helpful!!

[PintuKumar-qdym]

First of all great lecture series am kind of glued to it. Am not very clear with function low(i) at 35:49, from the terminology intuitively it appears it should be the smallest number of a column. But from the calculation, it appears like it's the bottom-most non zero element of that column. Just wanted to confirm am interpreting it right

[BringerOfBloood]

Thanks a lot for these lectures! They are very pedagogical and interesting.

[tongzhu]

I am doing the algorithm myself on 35:50, and I get a different result, and the reason would be that we go from i=1 and I think we should increment i by one each time???

Can you explain more on this? Thanks.

[greysonliu]

Thanks for the video! Do we need to standardize our dataset before generating the persistent diagram?

[dyllanusher]

Great lecture! Do you recommend any resources on learning how functors are becoming increasingly relevant for machine learning?

[alberto]

Great lectures! I've been offered a course in topology applied to big data in my college, would you recommend me to go for it?, I mean, does it have good career prospects?