Filters








5 Hits in 1.0 sec

Active Divergence with Generative Deep Learning – A Survey and Taxonomy [article]

Terence Broad, Sebastian Berns, Simon Colton, Mick Grierson
2021 arXiv   pre-print
Generative deep learning systems offer powerful tools for artefact generation, given their ability to model distributions of data and generate high-fidelity results.  ...  use deep generative models in truly creative systems.  ...  Acknowledgements We thank our reviewers for their helpful comments.  ... 
arXiv:2107.05599v1 fatcat:vfsapuewi5btvbmqe2ehtsvr5m

BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty [article]

Théo Guénais, Dimitris Vamvourellis, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan
2020 arXiv   pre-print
We propose a Bayesian framework to obtain reliable uncertainty estimates for deep classifiers.  ...  Traditional training of deep classifiers yields overconfident models that are not reliable under dataset shift.  ...  Creativeai: Deep learning for graphics. In SIGGRAPH 2019 Courses, Siggraph 2019, 2019.  ... 
arXiv:2007.06096v1 fatcat:ejzuirw7gveyhfaemp4toqkcni

The Nooscope manifested: AI as instrument of knowledge extractivism

Matteo Pasquinelli, Vladan Joler
2021
"Today, an Intelligent Machinery Question is needed to develop more collective intelligence about machine intelligence, more public education instead of 'learning machines' and their regime of knowledge  ...  Strubell, Energy and policy considerations for deep learning in NLP (2019). arXiv preprint; arXiv:1906.02243. Fig. 6 .Fig 8 : 68 World Vector space of seven words in three contexts.  ...  Fig. the convolutional architecture dates back to Yann Le-Cun's work in the late 1980s, Deep Learning starts with this paper: with deep convolutional neural networks.  ... 
doi:10.11588/ic.2021.3.81326 fatcat:gf5pae2qtvfhhfzptkdv36acme

An Introduction to Deep Generative Modeling [article]

Lars Ruthotto, Eldad Haber
2021 arXiv   pre-print
Some advances have even reached the public sphere, for example, the recent successes in generating realistic-looking images, voices, or movies; so-called deep fakes.  ...  Deep generative models (DGM) are neural networks with many hidden layers trained to approximate complicated, high-dimensional probability distributions using a large number of samples.  ...  Improved techniques for training gans. pages 2234–2242, 2016. [43] SmartGeometry at UCL. CreativeAI: Deep Learning for Graphics Tutorial Code. https://github. com/smartgeometry-ucl/dl4g.  ... 
arXiv:2103.05180v2 fatcat:mw222a5janhsxjahnehtyofxlq

Authors and Machines

Jane C. Ginsburg, Luke Ali Budiardjo
2018 Social Science Research Network  
Unlike other machine learning algorithms, which only have one or two layers, deep learning is "deep" because it has multiple layers --typically between 10 and 100 layers."). machine is partially self-tuning  ...  Machine Learning and the "Black The development of sophisticated generative machines utilizing machine-learning techniques like "deep learning" does not change this analysis.  ... 
doi:10.2139/ssrn.3233885 fatcat:k5fe5jd3dze35jhjuthbzbb67q