Skip to main content

Natural Signal Properties and the Convolutional Net

Difficulty level
Intermediate
Duration
1:09:12

This lecture discusses the concept of natural signals properties and the convolutional nets in practice and is a part of the Deep Learning Course at NYU's Center for Data Science.

Topics covered in this lesson

Chapters:

00:00 – Happy birthday to the TAs!
01:24 – Today topic: convolutional neural nets
2:37 – Input layer, points, and signals 1
9:21
– 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