Tag Archives: paper

Kanerva++ at ICLR21

The ICLR21 conference is still a few weeks away but to wet your appetite already, we are glad to let you know that Jason Ramapuram will be presenting there his new paper Kanerva++: Extending the Kanerva Machine With Differentiable, Locally Block Allocated Latent Memory. The paper is a result of a successful collaboration with Yan Wu from Deepmind.

Continue reading

Posted in news | Tagged , , , , , | Comments Off on Kanerva++ at ICLR21

Jason to present DAB

A couple of months ago Jason Ramapuram interned in Apple Machine Learning Research. Among other things, he worked with Russ Webb on a  novel method allowing for the use of simple non-differentiable functions at intermediary layers of deep neural networks. … Continue reading

Posted in news | Tagged , , , , , , | Comments Off on Jason to present DAB

Paper presentation in ACML 2019

Amina presented her recent work Learning to Augment with Feature Side-information in this year's edition of ACML, which took place in the beautiful Nagoya, in Japan. Attending this conference has been a great opportunity to follow the latest advancements of the field, … Continue reading

Posted in news | Tagged , , , , , | Comments Off on Paper presentation in ACML 2019

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!

Continue reading

Posted in news | Tagged , , , , , | Comments Off on Variational saccading