2020
Looking into development of generative networks capable of learning relevant semantic features of La Sagrada Familia at different scales.
#generativeadversarialnetworks #nonstandardstudio
#neuralnetworks #deeplearning
2019
#generativeadversarialnetworks #nonstandardstudio
#neuralnetworks #deeplearning #agentbasedsystem
2019
Looking into development of generative networks capable of learning relevant semantic features of La Sagrada Familia at different scales.
#generativeadversarialnetworks #nonstandardstudio
#neuralnetworks #deeplearning
Meet Deep Himmelb(l)au. Our algorithm learns CHBL’s semantic characteristics to generate new interpretations and new worlds.
Great improvement of the DeepHimmelb(l)au network that I’ve been building recently at Wolf D. Prix / Coop Himmelb(l)au. DeepHimmelblau is now able to learn an enormous amount of semantic characteristics to create more detailed interpretations
3D Domain Translation using Cycle-Consistent Adversarial Networks
Some of the algorithms I started developing while at I.sd Institute of Structure and Design, Innsbruck.
The 3D Domain Translation model starts to show some promising results. Although still more work is needed to be done to allow for a better disentanglement of features.
This approach builds on the work of Jun-Yan Zhu, Taesung Park, Philip Isola, Alexei A. Efros from Berkeley Ai Research (Bair) Laboratory, UC Berkeley
More detailed description soon…