Convolutional Neural Networks - learn about it from Yann LeCun

The video below is the week 3 lecture in the NYU Deep Learning course from 2020.  The lecture is given by Yann LeCun, who is really the father of convolutional neural networks.

It starts off a little bit strange, first with a demo by Alfredo Canziani of what a simple multi-layer linear net is doing in a visualization, and then Yann starts talking about 'when the parameter vector is the output of a function', and i was a little bit confused because i did not expect this was how it was going to start.  But then it pulls together (Yann is really talking about weight sharing architectures in that beginning section), and Yann dives into a really interesting presentation on convolutional neural networks.

Yann's implementation of convolutional neural networks was highly influenced by research on how the primate and human visual system works.  And by the associated work of the NeoCognitron architecture developed by Fukushima in the early 80's.

The slide below brought back a lot of memories for me, since this was the world i lived in for many years.  That slide could have been taken from one of my talks in the 90's, where i discussed how to incorporate results from human visual modeling into engineering systems.


Popular posts from this blog

Simulating the Universe with Machine Learning

CycleGAN: a GAN architecture for learning unpaired image to image transformations

Pix2Pix: a GAN architecture for image to image transformation