Scientific work that deepens the methods behind our applied R&D.
ComplexitySoft Research supports internal scientific investigation, methodological development and collaboration with external researchers and institutions.
ComplexitySoft Research is our internal research track, where we develop and investigate methods, models and scientific questions that expand the capabilities we bring to applied R&D.
ComplexitySoft Research
Work produced under ComplexitySoft Research and presented with ComplexitySoft affiliation.
Investigates the relationship between the structural maturation of complex neural networks — modeled with Liquid State Machines — and temporal perception.
Evidence
Examines how the availability of visual information relates to gaze behavior and the hierarchical organization of facial exploration in emotion recognition, combining eye tracking and psychophysics.
Evidence
Research
Liquid State Machines, structural maturation of neural networks and temporal perception.
Experimental design, gaze-data processing, fixation/AOI analysis, visualization and behavioral interpretation.
Graph-based classification, structural outlier detection and community detection in multilayer networks.
Visual perception, facial processing, signal detection theory, psychometric methods and quantitative behavioral analysis.
Research by our team
Relevant research by current team members that predates, or is not formally affiliated with, ComplexitySoft.
A line of research using complex-network representations and graph-based analysis for classification and for detecting structural outliers, including community detection in multilayer networks.
Evidence
Eye-tracking and gaze-contingent psychophysics research investigating how restricting the visual field affects the recognition of facial expressions.
Research
A Tourist Walk Approach for Internal and External Outlier Detection
Complex Network-based Classification of Radiographic Images for COVID-19 Diagnosis
Visual Field Restriction in Facial Expression Recognition
Research
A difficult problem may require both scientific domain reasoning and computational method development. Our joint eye-tracking research is the clearest example of how we work across disciplines.
In that work, responsibilities divide naturally:
Scientific domain reasoning
Computational method development
We welcome collaboration with universities, laboratories and external researchers on problems that benefit from this combination. For research collaboration, write to research@complexitysoft.com.
Research
Founder | AI Research & Strategy
Scientific & Data Science Collaborator
For applied R&D, write to contact@complexitysoft.com.
For scientific collaboration, write to research@complexitysoft.com.