Profile cover photo
Profile photo
Ludovic Guégan
179 followers -
Improving the cost function
Improving the cost function

179 followers
About
Ludovic's posts

Post has attachment

Post has shared content
- neural networks - - feed forward neural networks (FF or FFNN) and perceptrons (P)
Rosenblatt, Frank. “The perceptron: a probabilistic model for information storage and organization in the brain.” Psychological review 65.6 (1958): 386
http://www.ling.upenn.edu/courses/cogs501/Rosenblatt1958.pdf

- radial basis function (RBF)
Broomhead, David S., and David Lowe. Radial basis functions, multi-variable functional interpolation and adaptive networks. No. RSRE-MEMO-4148. ROYAL SIGNALS AND RADAR ESTABLISHMENT MALVERN (UNITED KINGDOM), 1988.
http://www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA196234

- a Hopfield network (HN)
Hopfield, John J. “Neural networks and physical systems with emergent collective computational abilities.” Proceedings of the national academy of sciences 79.8 (1982): 2554-2558.
https://bi.snu.ac.kr/Courses/g-ai09-2/hopfield82.pdf

- markov chains (MC or discrete time Markov Chain, DTMC)
Hayes, Brian. “First links in the Markov chain.” American Scientist 101.2 (2013): 252.
http://www.americanscientist.org/libraries/documents/201321152149545-2013-03Hayes.pdf

- Generative adversarial networks (GAN)
Goodfellow, Ian, et al. “Generative adversarial nets.” Advances in Neural Information Processing Systems. 2014.
https://arxiv.org/pdf/1406.2661v1.pdf

- - Boltzmann machines (BM)
Hinton, Geoffrey E., and Terrence J. Sejnowski. “Learning and releaming in Boltzmann machines.” Parallel distributed processing: Explorations in the microstructure of cognition 1 (1986): 282-317.
https://www.researchgate.net/profile/Terrence_Sejnowski/publication/242509302_Learning_and_relearning_in_Boltzmann_machines/links/54a4b00f0cf256bf8bb327cc.pdf

- Restricted Boltzmann machines (RBM)
Smolensky, Paul. Information processing in dynamical systems: Foundations of harmony theory. No. CU-CS-321-86. COLORADO UNIV AT BOULDER DEPT OF COMPUTER SCIENCE, 1986.
http://www.dtic.mil/cgi-bin/GetTRDoc?Location=U2&doc=GetTRDoc.pdf&AD=ADA620727

- autoencoders (AE)
Bourlard, Hervé, and Yves Kamp. “Auto-association by multilayer perceptrons and singular value decomposition.” Biological cybernetics 59.4-5 (1988): 291-294.

https://pdfs.semanticscholar.org/f582/1548720901c89b3b7481f7500d7cd64e99bd.pdf

- Sparse autoencoders (SAE)
Marc’Aurelio Ranzato, Christopher Poultney, Sumit Chopra, and Yann LeCun. “Efficient learning of sparse representations with an energy-based model.” Proceedings of NIPS. 2007.
https://papers.nips.cc/paper/3112-efficient-learning-of-sparse-representations-with-an-energy-based-model.pdf

- variational autoencoders (VAE)
Kingma, Diederik P., and Max Welling. “Auto-encoding variational bayes.” arXiv preprint arXiv:1312.6114 (2013).

https://arxiv.org/pdf/1312.6114v10.pdf

- denoising autoencoders (DAE)
Vincent, Pascal, et al. “Extracting and composing robust features with denoising autoencoders.” Proceedings of the 25th international conference on Machine learning. ACM, 2008.
http://machinelearning.org/archive/icml2008/papers/592.pdf

- deep belief networks (DBN)
Bengio, Yoshua, et al. “Greedy layer-wise training of deep networks.” Advances in neural information processing systems 19 (2007): 153.
https://papers.nips.cc/paper/3048-greedy-layer-wise-training-of-deep-networks.pdf

- deconvolutional networks (DN),
Zeiler, Matthew D., et al. “Deconvolutional networks.” Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. IEEE, 2010.
http://www.matthewzeiler.com/pubs/cvpr2010/cvpr2010.pdf

-Deep convolutional inverse graphics networks (DCIGN)
Kulkarni, Tejas D., et al. “Deep convolutional inverse graphics network.” Advances in Neural Information Processing Systems. 2015.
https://arxiv.org/pdf/1503.03167v4.pdf

cr: asimovorg


Photo

Post has attachment

Post has attachment
Wondering if golang is vulnerable to FREAK? Relax :)

Post has attachment

Post has attachment

Post has attachment
L'édito de Jean-Louis Frechin, commissaire de Futur en Seine du 12 au 15 juin.

Changer de manière de voir et de « faire les choses », agir et partager, c’est ce que nous vous proposons pour la 5e édition de Futur en Seine, le festival mondial du numérique. Cause ou conséquence, les crises multiples que nous subissons et les manières dont le « numérique » modifie ce que nous connaissons nécessitent une remise en question « historique » de nos productions, de nos modèles et de nos organisations issues du XXe siècle. Le numérique est autant une révolution culturelle et sociale qu’une nouvelle révolution industrielle et économique. L’esprit du numérique modifie en profondeur tous les secteurs de la société et redéfinit les façons dont nous devons « fabriquer les choses ».

Post has attachment
Maritime Robotics.

We do really need to clean the oceans: what a clairvoyant idea!

Post has attachment
InMoov robot  at Wevolver: Open hardware projects.

To accelerate the diffusion of InMoov, parts are now accessible at on this platform.

Post has attachment
Mechatronic design of an integrated
robotic hand.

Really interesting analysis a robot hand. This remarkable design use a camera and a FPGA inside the hand to allow visual feed-back with local image processing. Once again with the contribution of Andrew Ng, thanks!
Wait while more posts are being loaded