Equivariant Neural Networks for Inverse Problems
Duration: 48 mins 43 secs
Share this media item:
Embed this media item:
Embed this media item:
About this item
| Description: |
Dr Matthias Ehrhardt (University of Bath)
29th September 2021 | 11:00 - 11:40 |
|---|
| Created: | 2021-10-26 10:21 |
|---|---|
| Collection: | Mathematics of deep learning |
| Publisher: | Isaac Newton Institute for Mathematical Sciences |
| Copyright: | Dr Matthias Ehrhardt |
| Language: | eng (English) |
| Abstract: | In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of this approach have motivated a line of research into incorporating other symmetries into deep learning methods, in the form of group equivariant convolutional neural networks. In this work, we demonstrate that roto-translational equivariant convolutions can improve reconstruction quality compared to standard convolutions when used within a learned reconstruction method. This is almost a free lunch since only little extra computational cost during training and absolutely no extra cost at test time is needed. |
|---|---|
Available Formats
| Format | Quality | Bitrate | Size | |||
|---|---|---|---|---|---|---|
| MPEG-4 Video | 1280x720 | 2.21 Mbits/sec | 808.32 MB | View | Download | |
| MPEG-4 Video | 640x360 | 888.86 kbits/sec | 317.16 MB | View | Download | |
| WebM | 1280x720 | 2.08 Mbits/sec | 760.50 MB | View | Download | |
| WebM | 640x360 | 563.57 kbits/sec | 201.16 MB | View | Download | |
| iPod Video | 480x270 | 480.98 kbits/sec | 171.62 MB | View | Download | |
| MP3 | 44100 Hz | 249.73 kbits/sec | 89.23 MB | Listen | Download | |
| Auto * | (Allows browser to choose a format it supports) | |||||