| Link | https://s2d-olad.github.io/papers/submission-13.pdf |
|---|
| Author | Search for: Al-Digeil, Muhammad1; Search for: Grinberg, Yuri1; Search for: Kamandar Dezfouli, Mohsen2; Search for: Melati, Daniele; Search for: Schmid, Jens H.2; Search for: Cheben, Pavel2; Search for: Janz, Siegfried2; Search for: Xu, Dan-Xia2 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
- National Research Council of Canada. Advanced Electronics and Photonics
|
|---|
| Format | Text, Article |
|---|
| Conference | Ninth International Conference on Learning Representations 2021, May 3-7, 2021, Virtual Only |
|---|
| Abstract | Principal Component Analysis (PCA) provides reliable dimensionality reduction (DR) when data possesses linear properties even for small datasets. However, faced with data that exhibits non-linear behaviour, PCA cannot perform optimally as compared to non-linear DR methods such as AutoEncoders. By contrast, AutoEncoders typically require much larger datasets for training than PCA. This data requirement is a critical impediment in applications where samples are scarce and expensive to come by. One such area is nanophotonics component design where generating a single data point might involve running optimization methods that use computationally demanding solvers. We propose Guided AutoEncoders (G-AE) of nearly arbitrary architecture which are standard AutoEncoders initialized using a numerically stable procedure to replicate PCA behaviour before training. Our results show this approach yields a marked reduction in the data size requirements for training the network along with gains in capturing non-linearity during dimensionality reduction and thus performing better than PCA alone. |
|---|
| Publication date | 2021-05 |
|---|
| Publisher | International Conference on Learning Representations |
|---|
| Other format | |
|---|
| Language | English |
|---|
| Peer reviewed | No |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 1e0df489-1401-4852-b02f-9486d0f5b46b |
|---|
| Record created | 2022-05-30 |
|---|
| Record modified | 2023-07-27 |
|---|
