🇬🇧   🇫🇷

This semester we have reorganised the didactic material. In the first half of the semester we covered 3 topics, spanning two weeks, each followed by an assignment. Moreover, each lecture had a corresponding practicum.

1. History, backpropagation, and gradient descent
2. Parameter sharing: recurrent and convolutional networks
3. Latent variable (LV) energy based models (EBMs)

Pay attention that we have redesigned the curriculum and lectures' content. We've treated LV-EBM as a basic module, which to build upon.

I thought I was going to repropose the same practica I've used during NYU-DLSP20, last year edition, just in different order.

But I couldn't.

This year's students have LV-EBMs on their side. We told them about the cake and now I cannot pretend it doesn't exist and teach as if they were unaware of the elephant in the room. It would have been intellectually dishonest. Henceforth, I've redesigned my whole deck of slides.

That's why this repo has been created. I'm not going to try to do the same insane work I've put up with last year, but I need a space where to post updated slides, notebooks, and host new transcriptions. Last year material is still valid. This year you have a different take. A more powerful one.

Before NYU-DLSP21 there were…

• NYU-DLSP20 (major release)
• NYU-DLSP19
• AIMS-DLFL19
• CoDaS-HEP18
• NYU-DLSP18
• Purdue-DLFL16
• torch-Video-Tutorials

Keep reading on the class website.