nonstandardstudio
nonstandardstudio
notes_links_tweets_favorites
www.nonstandardstudio.wordpress.com
262 posts
Don't wanna be here? Send us removal request.
Last Seen Blogs
heretic-altias
A Heretic
lylelylelyle
Lyle
2686collective-blog
26:86 Collective
tsnon
Mildly Respectful.
ninjaturtlemaniac
NinjaTurtleManiac
Text
Structurally Encoded Agents
Structurally Encoded Agents – Using a neural network to train a multi agent system to be structurally aware and encode structural heuristics as behaviors within an agent.
View On WordPress
#tensorflow#fem#nonstandardstudio#structurallyencodedagents#topologyoptimization#vae#variationalautoencoder
0 notes
Text
Design Space Explorer - Multi-agent Systems
Design Space Explorer – Multi-agent Systems
Design Space Explorer – Multi-agent Systems
This approach represents a shift from the idea of a design as a output, to the idea of design as multiple outputs, designer engaging into a process of selection.
The role of Creativity in this design process is to defining the constraints that generate a range of possible solutions for a design problem, and define and develop strategies and effective…
View On WordPress
1 note
·
View note
Text
Current on-going research focusing on unsupervised learning algorithms in order to classify and cluster behavioral inputs and integrate them within the design process, as a form finding phase through a non-linear morph of behavior parameters.
AGENT BASED SYSTEMS COUPLED WITH MACHINE LEARNING ALGORITHMS
Self-organizing maps (SOM) are used here, (SOM 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. 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 systems parameters by the designer.
The selected 8 models are used as inputs for the SOM. The resulting map create a interpolation between inputs and creates a location rule, placing similar models closer on the map while placing further apart dissimilar models.
AGENT BASED SYSTEM TRACEFOLLOW BEHAVIOR PARAMETERS
VIEW ANGLE
COHESION MAGNITUDE
COESHION VIEW RANGE
SEPARATION MAGNITUDE
SEPARATION VIEW RANGE
FIELD MIN INTENSITY
FIELD MAX INTENSITY
STEP MAGNITUDE
OVERALL SYSTEM LENGTH
COLOR START
COLOR END
BEHAVIOR PARAMETERS INFLUENCE DISTRIBUTION
K-mean clustering is use here to analyse parameter distributions on the self organizing map (SOM), and help cluster and classify insightful behavioral patterns, and quantify the influence each have on the outcome.
#java #python #tensorflow #som #unsupervisedlearning #multiagentalgorithms #behavior
AGENT BASED SYSTEMS COUPLED WITH MACHINE LEARNING ALGORITHMS Current on-going research focusing on unsupervised learning algorithms in order to classify and cluster behavioral inputs and integrate them within the design process, as a form finding phase through a non-linear morph of behavior parameters.
0 notes
Text
Machine Learning for generative design
Machine Learning for generative design
In this case 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 represent a type of unsupervised artificial neural network), to reduce the high dimensionality of the…
View On WordPress
0 notes
Text
SNA - MachineLearning - Dimensionality reduction
SNA – MachineLearning – 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 variable 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…
View On WordPress
0 notes
Video
Parametric semiology – strange attractors – stress resposiveness
0 notes
Text
surface active tesselation 004
surface active tesselation 004
View On WordPress
#bolojan daniel#nonstandardstudio#nss#object oriented programming#parametric design#processing#space frame#structural#studio zaha hadid#surface active tesselation
0 notes
Text
GPGPU - Agent bodies facade
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 GTX780Tiused in this study, having in total a combined 5760CUDA cores (2880 each),…
View On WordPress
0 notes
Text
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 –…
View On WordPress
0 notes
Text
GPGPU - Structurally encoded agent bodies
GPGPU – Structurally encoded agent bodies
Couple iterations of a Pavilion studies that we did last year. Full project pictures will be presented soon. #agentbodies #swarm #swarmintelligence #informedbodies #chargedfields #java #jCuda nonstandardstudio more description soon… 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 i7-4960X @ 3.60GHz and…
View On WordPress
0 notes
Text
Agent Morphologies 2
View On WordPress
0 notes
Text
GPGPU - Sematectonic Fields - Smart Agent Bodies
GPGPU – Sematectonic Fields – Smart Agent Bodies
View On WordPress
0 notes
Text
Ubiquitous nearness
View On WordPress
#nearestvector#bottom up design#generative algorithms#generative design#grasshopper#nonstandardstudio#nss#parametric design
0 notes