Binding the Person-Specific Approach to Modern AI in the Human Screenome Project: Moving past Generalizability to Transferability.

Advances in ability to comprehensively record individuals' digital lives and in AI modeling of those data facilitate new possibilities for describing, predicting, and generating a wide variety of behavioral processes. In this paper, we consider these advances from a person-specific perspective, including whether the pervasive concerns about generalizability of results might be productively reframed with respect to transferability of models, and how self-supervision and new deep neural network architectures that facilitate transfer learning can be applied in a person-specific way to the super-intensive longitudinal data arriving in the Human Screenome Project. In developing the possibilities, we suggest Molenaar add a statement to the person-specific Manifesto - "In short, the concerns about generalizability commonly leveled at the person-specific paradigm are unfounded and can be fully and completely replaced with discussion and demonstrations of transferability."

[1]  Liang Huang,et al.  Transformer-Based Generative Model Accelerating the Development of Novel BRAF Inhibitors , 2021, ACS omega.

[2]  Byron Reeves,et al.  Time for the Human Screenome Project , 2020, Nature.

[3]  C. Lee Giles,et al.  Screenomics: A Framework to Capture and Analyze Personal Life Experiences and the Ways that Technology Shapes Them , 2019, Hum. Comput. Interact..

[4]  Mikhail Belkin,et al.  Reconciling modern machine-learning practice and the classical bias–variance trade-off , 2018, Proceedings of the National Academy of Sciences.

[5]  C. Lee Giles,et al.  How are you feeling?: A personalized methodology for predicting mental states from temporally observable physical and behavioral information , 2017, J. Biomed. Informatics.

[6]  J. Pearl,et al.  Causal inference and the data-fusion problem , 2016, Proceedings of the National Academy of Sciences.

[7]  Ha Hong,et al.  Performance-optimized hierarchical models predict neural responses in higher visual cortex , 2014, Proceedings of the National Academy of Sciences.

[8]  Michael J. Roche,et al.  Examining the Interplay of Processes Across Multiple Time-Scales: Illustration With the Intraindividual Study of Affect, Health, and Interpersonal Behavior (iSAHIB) , 2014, Research in human development.

[9]  Kathleen M. Gates,et al.  Group search algorithm recovers effective connectivity maps for individuals in homogeneous and heterogeneous samples , 2012, NeuroImage.

[10]  D. A. Kenny,et al.  Treating stimuli as a random factor in social psychology: a new and comprehensive solution to a pervasive but largely ignored problem. , 2012, Journal of personality and social psychology.

[11]  Kathleen M. Gates,et al.  Automatic search for fMRI connectivity mapping: An alternative to Granger causality testing using formal equivalences among SEM path modeling, VAR, and unified SEM , 2010, NeuroImage.

[12]  P. Molenaar.  A Manifesto on Psychology as Idiographic Science: Bringing the Person Back Into Scientific Psychology, This Time Forever , 2004 .

[13]  Simant Dube,et al.  An Intuitive Exploration of Artificial Intelligence: Theory and Applications of Deep Learning , 2021 .

[14]  Timothy R Brick,et al.  Feature Selection Methods for Optimal Design of Studies for Developmental Inquiry , 2017, The journals of gerontology. Series B, Psychological sciences and social sciences.

[15]  P. Molenaar,et al.  Analyzing developmental processes on an individual level using nonstationary time series modeling. , 2009, Developmental psychology.