DecNefSimulator: A Modular, Interpretable Framework for Decoded Neurofeedback Simulation Using Generative Models

2025/11/18 by Olza, Alexander, Santana, Roberto, Soto, David
Neuroscience · #Artificial Intelligence (cs.AI) #EEG and Brain-Computer Interfaces #FOS: Biological sciences #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Neural and Behavioral Psychology Studies #Neurons and Cognition (q-bio.NC)

paper · doi:10.48550/arxiv.2511.14555

openalex publication_date 2025/11/18 · openalex created_date 2025/11/20 · openalex updated_date 2026/07/28

Abstract

Decoded Neurofeedback (DecNef) is a promising non-invasive approach to brain modulation with wide-ranging applications in neuromedicine and cognitive neuroscience. However, progress in DecNef research remains constrained by subject-dependent learning variability, reliance on indirect measures to quantify progress, and the high cost and time demands of experimentation. We present DecNefSimulator, a modular and interpretable simulation framework that formalizes DecNef as a machine learning problem. Beyond providing a virtual laboratory, DecNefSimulator enables researchers to model, analyze and understand neurofeedback dynamics. Using latent variable generative models as simulated participants, DecNefSimulator allows direct observation of internal cognitive states and systematic evaluation of how different protocol designs and subject characteristics influence learning. We demonstrate how this approach can (i) reproduce empirical phenomena of DecNef learning, (ii) identify conditions under which DecNef feedback fails to induce learning, and (iii) guide the design of more robust and reliable DecNef protocols in silico before human implementation. In summary, DecNefSimulator bridges computational modeling and cognitive neuroscience, offering a principled foundation for methodological innovation, robust protocol design, and ultimately, a deeper understanding of DecNef-based brain modulation.

Citations

• SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
• Visual Image Reconstruction from Brain Activity via Latent Representation
• An Active Inference perspective on Neurofeedback Training
• MindSimulator: Exploring Brain Concept Localization via Synthetic FMRI
• Ornstein-Uhlenbeck Adaptation as a Mechanism for Learning in Brains and Machines
• Domain Adaptation-Enhanced Searchlight: Enabling classification of brain states from visual perception to mental imagery
• Natural scene reconstruction from fMRI signals using generative latent diffusion
• Neurofeedback through the lens of reinforcement learning
• Variational Diffusion Models
• Active Inference Tree Search in Large POMDPs
• Learning Transferable Visual Models From Natural Language Supervision
• Hierarchical VAEs Know What They Don't Know
• Analysis of Dominant Classes in Universal Adversarial Perturbations
• Generative embeddings of brain collective dynamics using variational\n autoencoders
• Exploration versus exploitation in reinforcement learning: a stochastic control approach
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Universal adversarial perturbations
• Adversarially Learned Inference

Related

• Generative AI-based closed-loop fMRI system
• Decoded fMRI neurofeedback can induce bidirectional behavioral changes within single participants
• An Active Inference perspective on Neurofeedback Training
• Neurofeedback: principles, appraisal and outstanding issues
• Cognitive computational neuroscience