NYU Deep Learning SP21 - 04.1 – Natural signals properties and the convolution

Course website: http://bit.ly/DLSP21-web Playlist: http://bit.ly/DLSP21-YouTube Speaker: Alfredo Canziani Chapters 00:00 – Happy birthday to the TAs! 01:24 – Today topic: convolutional neural nets 2:37 – Input layer, points, and signals 19:21 – Natural signal properties 20:48 – 1D stationarity 21:30 – 1D locality 23:39 – 2D stationarity 25:04 – 2D locality 26:56 – 2D compositionality 31:17 – Fully connected recap 33:10 – Locality ⇒ sparsity 39:41 – Stationarity ⇒ parameter sharing 45:13 – 1D kernels 50:56 – 1D padding 53:18 – ConvNet for images and tensor reshaping 56:17 – Pooling 58:21 – Jupyter Notebook: fully connected vs. convnet 1:05:36 – Deterministic pixel shuffling: breaking signal properties 1:06:49 – Final comparison 1:08:35 – Goodbye