-
Archives
- January 2024
- December 2023
- September 2023
- June 2023
- April 2023
- March 2023
- January 2023
- December 2022
- November 2022
- October 2022
- August 2022
- June 2022
- May 2022
- April 2022
- February 2022
- December 2021
- September 2021
- August 2021
- April 2021
- March 2021
- February 2021
- December 2020
- November 2020
- October 2020
- September 2020
- August 2020
- July 2020
- May 2020
- February 2020
- January 2020
- December 2019
- November 2019
- October 2019
- September 2019
- August 2019
- July 2019
- May 2019
- April 2019
- November 2018
- October 2018
- August 2018
- June 2018
- May 2018
- February 2018
- January 2018
- November 2017
-
Meta
Tag Archives: Variational saccading
PhD Thesis defense of Jason Ramapuram
Jason Ramapuram will defend on Wednesday the 15th of September 2021 at 13:00 his PhD thesis entitled: "Finding signals in the void: Improving deep latent variable generative models via supervisory signals present within data." co-directed by Prof. Stephane Marchand-Maillet and … Continue reading
Posted in events, news
Tagged Alexandros Kalousis, deep leaning, generative modeling, Jason, Jason Ramapuram, Kanerva++, phd, PhD Thesis, presentation, VAE, Variational saccading
Comments Off on PhD Thesis defense of Jason Ramapuram
Variational saccading
Ever tried to train a deep neural network over high resolution images taken by modern smartphone cameras or smart devices? The memory and inferential costs when working with inputs of such large dimensions (e.g. 4000x3000) increase rapidly and often prohibitively. Jason Ramapuram proposes a solution in his new paper "Variational Saccading: Efficient Inference for Large Resolution Images". He will present his idea at the BMVC conference in September this year but you don't have to wait, check out the preprint!
Posted in news
Tagged BMVC conference, conference, Jason, Jason Ramapuram, paper, Variational saccading
Comments Off on Variational saccading