Probabilistic Inference & Control (and lots of open source) - PowerPoint PPT Presentation

Probabilistic Inference & Control (and lots of open source) Patrick van der Smagt Director of AI Research Volkswagen Group Data Lab Munich

CNNs proved to excel in supervised image classification

great results from deep learning with Q-learning

Kacelnik / Auersperg / von Bayern U. Oxford / U Vienna

“ tufa” “ tufa” “tufa” can you pick out the tufas? from Josh Tenenbaum, but I first saw it from Nando de Freitas

"understand" what you see

unsupervised Deep Variational Bayes Filtering: filtering in latent space of a variational autoencoder ~ ~ ~ system state x(t+1) system state x(t+2) system state x(t) ~ ~ p(z(t+1)) p(z(t+2)) filter filter p(z(t)) back- propagation system state x(t) system state x(t+1) system state x(t+2) Karl & Soelch & Bayer & van der Smagt, ICLR 2017

unsupervised DVBF: coding in latent space inverted pendulum dynamics learned from images Karl & Soelch & Bayer & van der Smagt, ICLR 2017

control through DVBF: exploration

unsupervised control through DVBF: Erwin Schrödinger, 1944: Negentropy after unsupervised learning with Empowerment Klyubin et al, 2005: Empowerment Wissner-Gross et al, 2013: Causal Entropic Forces p ( s 0 | s, a ) ln p ( s 0 | s, a ) Z Z p ( s 0 | s ) ds 0 da C ( s ) := max p ( a | s ) p ( a | s ) KL-divergence between maximises information gain Z ⇥ ⇤ p ( s 0 | s, a ) k p ( s 0 | s ) = max p ( a | s ) KL p ( a | s ) Karl et al, AISTATS 2018

we're reaching out • www.argmax.ai • Maximilian Karl, Maximilian Soelch, Justin Bayer, Patrick van der Smagt (2017) 
 Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data 
 International Conference on Learning Representations (ICLR) • Baris Kayalibay, Grady Jensen, Patrick van der Smagt (2017) 
 CNN-based Segmentation of Medical Imaging Data 
 arXiv • Nutan Chen, Maximilian Karl, Patrick van der Smagt (2016) 
 Dynamic Movement Primitives in Latent Space of Time-Dependent Variational Autoencoders 
 Proc. 16th IEEE-RAS International Conference on Humanoid Robots • collaboration in European projects and with TUM, DLR, TU Berlin, U Berkeley, NVIDIA, DeepMind, U Edinburgh, U Freiburg, LMU, Umeå University, ... • open-sourcing our so fu ware, to promote its deployment and further development

"unrelated" open-source project: sigma—learning how computers learn Florian Cäsar and Michael Plainer HTL Wels, Austria https://sigma.rocks/ https://github.com/ThinkingTransistor/Sigma

"unrelated" open-source project: sigma—learning how computers learn CPU CPU #neurons per layer GPU GPU

Sigma awards • Best Project - National ITS Project Award 1st Prize • Best Science Project - National JugendInnovativ 1st Prize • EIROforum Special Donated Prize - International European Union Contest for Young Scientists • 3rd Prize - International European Union Contest for Young Scientists

the 2017 Deep Learning and Robotics Challenge organised by Volkswagen Group AI Research w/ NVIDIA support 31 blog posts 21 students 10 Mindstorms 10 Jetson TX-2 5 teams 5 1080's 4.5 weeks 1 DGX-1 1 task: unsupervised brick sorting many CNN's, RNN's, GMM's, VAE's, Kalman filters, SLAM, neural networks, PID, kNN, ...

2017 Deep Learning and Robotics Challenge

2017 Deep Learning and Robotics Challenge the winning team: Great Dolphins Kaboom Jonathon Luiten Lucia Seitz David Adrian Akshat Tandon Karolina Stosio

join us • http://argmax.ai • World Summit AI, Amsterdam, Oct. 11–12 • Munich City AI: http://munich.city.ai on Oct. 26