A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Reconstruct, Rasterize and Backprop: Dense shape and pose estimation from a single image
[article]
2020
arXiv
pre-print
Preserved Fulltext
This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image. ...
We demonstrate that our approach---dubbed reconstruct, rasterize and backprop (RRB) achieves significantly lower pose estimation errors compared to prior art, and is able to recover dense object shapes ...
Acknowledgment The authors acknowledge the support and funding from Kohli Center for Intelligent Systems (KCIS), IIIT Hyderabad for this work. ...
arXiv:2004.12232v1
fatcat:7p2ln75xfzcxbapf2ztksua6ge
Distilling Model Knowledge
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We present a general framework for knowledge distillation, whereby a convenient model of our choosing learns how to mimic a complex model, by observing the latter's behaviour and being penalized whenever ...
In this thesis, we study knowledge distillation, the idea of extracting the knowledge contained in a complex model and injecting it into a more convenient model. ...
learning (and beyond!). ...
arXiv:1510.02437v1
fatcat:c32papt6hngcre4wkl3nygac7a
Physics-based Deep Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This digital book contains a practical and comprehensive introduction of everything related to deep learning in the context of physical simulations. ...
Beyond standard supervised learning from data, we'll look at physical loss constraints, more tightly coupled learning algorithms with differentiable simulations, as well as reinforcement learning and uncertainty ...
As inputs we have the Reynolds number Re ∈ R, the angle of attack 𝛼 ∈ R, and the airfoil shape s encoded as a rasterized grid with 128 2 . ...
arXiv:2109.05237v3
fatcat:pz7ot63dlbdkriihkwloefk3im
2022 Roadmap on Neuromorphic Computing and Engineering
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2105.05956v2 fatcat:n5zeug6lnfgn3jvmnh2w6sckzyOther Versions
Among their potential future applications, an important niche is moving the control from data centers to edge devices. ...
The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic ...
Acknowledgements
Roadmap on Neuromorphic Computing and Engineering This work was partially based on results obtained from a project, JPNP16007, commissioned by the New Energy and Industrial Technology ...
arXiv:2105.05956v3
fatcat:pqir5infojfpvdzdwgmwdhsdi4
Putting more neural in artificial neural networks
[article]
2021
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
State-of-the-art algorithms in object recognition still suffer from interpreting images in a way that is not human-like, leading to unexpected and potentially catastrophic errors. ...
In this thesis, we work towards understanding how can we use AI algorithms as a model of the brain, and how can the brain influence how we design AI algorithms? ...
ACKNOWLEDGEMENTS This dissertation would not be possible without a significant amount of support from colleagues, friends and family. ...
doi:10.25677/byv1-e934
fatcat:4yhtnbzg2vaslh6vkiy2uepszu
Event-Based Vision Processing in Deep Neural Networks
2020
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The algorithm is shown to produce equivalent accuracy results at reduced computational cost on a range of vision tasks including human pose estimation and object detection in static and dynamic scenes. ...
The algorithm is shown to produce equivalent accuracy results at reduced computational cost on a range of vision tasks including human pose estimation and object detection in static and dynamic scenes. ...
. † On a subset of 2570 samples, using single-scale images of size 224x224. † † On a subset of 1382 samples, using single-scale images of size 299x299. ‡ On a subset of 3072 samples. ...
doi:10.5167/uzh-200987
fatcat:y2clxptcabh2bklipriywhtx4i
2022 roadmap on neuromorphic computing and engineering
2022
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Among their potential future applications, an important niche is moving the control from data centers to edge devices. ...
The aim of this roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic ...
Acknowledgements This research/project was supported by the Human Brain Project (Grant Agreement Number 785907) of the European Union and a Grant from Intel. ...
doi:10.3929/ethz-b-000529282
fatcat:x5s5lalqqbbn7fb6gmpqmbqkxu