August 2017

Aug 2017

Machine Learning for generative design

In this case, the autoencoder network is used to perform the task of dimensionality reduction, in combination with the parameters of a generative system (woolly threads), in order to visualize the high dimensional parameter space of these sort of system.

Self-organizing maps (SOM) are used here, (SOM represents a type of unsupervised artificial neural network), to reduce the high dimensionality of the data whilst also retain the high-dimensional non-linear associations. As SOMs can create associations between inputs, the map can suggest an overview of possibilities within the given parameter space, without the need of manually tweaking the system’s parameters by the designer.
The selected 7 models are used as inputs for the SOM. The resulting map creates an interpolation between inputs and creates a location rule, placing similar designs closer on the map while placing further apart dissimilar designs.

Parameters
– cutoff parameter
– stiffness parameter
– numToMove parameter
– num of control points parameter
– color parameter
– root location

#autoencoder #owl #machineLearning

As in the previous post, because the dataset was relatively small, I used only CPU ( 2 x Intel Core i7-4930k @ 3.40GHz) computing for training phase. If you are dealing with a big data set, a GPU might be a better way to go to train your dataset.

SNA – Machine Learning – Dimensionality reduction

Visualization of a social network analysis (SNA) defined by a high-dimensional parameter space (21 dimensions). Dimensionality reduction (DR) is used here to allow the reduction of the number of variables that defines a system, into a lower-dimensional space (2D). In this case, I’m using self-organizing maps (SOM), which represent a type of unsupervised artificial neural network, to reduce the high dimensionality of the data whilst also retain the high-dimensional non-linear associations.

Another feature extraction used (side by side image), is a linear feature extraction method -> K-means cluster analysis, (although linear methods don’t retain the associations distributed non-linearly in the high dimensional space). #owl #machinelearning

As the dataset was relatively small, I used only CPU ( 2 x Intel Core i7-4930k @ 3.40GHz) computing for the training phase. If you are dealing with a big data set, a GPU might be a better way to go to train your dataset. CPU – 2 x Intel Core i7-4930k @ 3.40GHz GPU – GPU

03_UnSupervised Learning - autoencoder 577 tensors 002.jpg

03_UnSupervised Learning - autoencoder 577 tensors 004

03_UnSupervised Learning - autoencoder 577 tensors 012.jpg

03_UnSupervised Learning - autoencoder 577 tensors 001.jpg

03_UnSupervised Learning - autoencoder 577 tensors 010.jpg

03_UnSupervised Learning - autoencoder 577 tensors 013.jpg

GPGPU – Agent bodies facade

Investigations into agent bodies algorithms, and behavioral algorithms, where gradients and levels of differentiation are not predefined but rather a result of emergence.
#GPGPU #Stigmergy #Java #agentbodies #selforganization #JCuda #sematectonicFields nonstandardstudio

more description soon…

There were 2xNVidia GTX780Ti used in this study, having in total a combined 5760 CUDA cores (2880 each), running on a machine 2 x Intel Core i7-4930k @ 3.40GHz and Corsair DOMINATOR Platinum Series 64GB DDR4 DRAM 2800MHz.

References:

[1]Emergence: The Connected Lives of Ants, Brains, Cities, and Software by Steven Johnson

[2]The Myth of the Framework: In Defense of Science and Rationality by Karl Popper

[3] Bonabeau E., M. Dorigo, G. Théraulaz. Swarm Intelligence: From Natural to Artificial System s. Santa Fe Institute in the Sciences of the Complexity, Oxford University Press, New York, Oxford, 1999.
[4] Chialvo, Dante R., Millonas, Mark M. “How Swarms Build Cognitive Maps” . In Luc Steels (Ed.), The Biology and Technology of Intelligent Autonomous Agents , (144) pp. 439-450, NATO ASI Series, 1995.
[5] Vitorino Ramos, Filipe Almeida, Artificial Ant Colonies in Digital Image Habitats – A Mass Behaviour Effect Study on Pattern Recognition, Proceedings of ANTS’2000 – 2nd International Workshop on Ant Algorithms (From Ant Colonies to Artificial Ants), Marco Dorigo, Martin Middendorf & Thomas Stüzle (Eds.), pp. 113 – 116, Brussels, Belgium, 7 – 9 Sep. 2000.

US equivalent
GPU: 2xNVidia GTX780Ti
CPU: 2 x Intel Core i7-4930k @ 3.40GH
RAM: Corsair DOMINATOR Platinum Series 64GB DDR4 DRAM 2800MHz

References:

[1]Emergence: The Connected Lives of Ants, Brains, Cities, and Software by Steven Johnson

[2]The Myth of the Framework: In Defense of Science and Rationality by Karl Popper

Structural Stigmergy Model

Structural Stigmergy Model nonstandardstudio #stigmergy #structuralStigmergy #shellStructures #catenary

Articulation of structural morphologies – through principles of stigmergic collaboration and structural coupling.

By self-regulating critical variables of force distribution within a structural system, the ecology of agents is developing an automatic mechanism of self-regulation – homeostasis/autopoiesis system – where the system becomes self-producing, allowing for a correlated and differentiated multi-system. Where like in natural systems, compositions are so highly integrated that they cannot be easily decomposed into independent subsystems. It becomes a system with self-reference and self-regulation which further evolves by using structural coupling. Therefore recognizing that the outside influences cannot shape the system’s internal structure, but act only as a trigger that causes the structure to alter its current attractors.

The ecology of agents allows us to correlate multiple systems, and encourage the contributive coexistence of different articulation layers.

There were 2xNVidia GTX780Ti used in this study, having in total a combined 5760CUDA cores (2880 each), running on a machine 2 x Intel Core i7-4930k @ 3.40GHz and Corsair DOMINATOR Platinum Series 64GB DDR4 DRAM 2800MHz.

References:

[1]Emergence: The Connected Lives of Ants, Brains, Cities, and Software by Steven Johnson

[2]The Myth of the Framework: In Defense of Science and Rationality by Karl Popper

US equivalent
GPU: 2xNVidia GTX780Ti
CPU: 2 x Intel Core i7-4930k @ 3.40GH
RAM: Corsair DOMINATOR Platinum Series 64GB DDR4 DRAM 2800MHz

References:

[1]Emergence: The Connected Lives of Ants, Brains, Cities, and Software by Steven Johnson

[2]The Myth of the Framework: In Defense of Science and Rationality by Karl Popper