Decoding Working Memory Load from EEG with LSTM Networks

Samuel Goldstein; Zhenhong Hu; Mingzhou Ding

Home/Archive/arXiv

arXiv · 1910.05621

Decoding Working Memory Load from EEG with LSTM Networks

Samuel Goldstein·Zhenhong Hu·Mingzhou Ding

View original source ↗Read source document ↗Export metadata ↓

Abstract

Working memory (WM) is a mechanism that temporarily stores and manipulates information in service of behavioral goals and is a highly dynamic process. Previous studies have considered decoding WM load using EEG but have not investigated the contribution of sequential information contained in the temporal patterns of the EEG data that can differentiate different WM loads. In our study, we develop a novel method of investigating the role of sequential information in the manipulation and storage of verbal information at various time scales and localize topographically the sources of the sequential information based decodability. High density EEG (128-channel) were recorded from twenty subjects performing a Sternberg verbal WM task with varying memory loads. Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) were trained to decode memory load during encoding, retention, activity-silent, and retrieval periods. Decoding accuracy was compared between ordered data and a temporally shuffled version that retains pattern based information of the data but not temporal relation to assess the contribution of sequential information to decoding memory load. The results show that (1) decoding accuracy increases with increase in the length of the EEG time series given to the LSTM for both ordered and temporally shuffled cases, with the increase being faster for ordered than temporally shuffled time series, and (2) according to the decoding weight maps, the frontal, temporal and some parietal areas are an important source of sequential information based decodability. This study, to our knowledge, is the first study applying a LSTM-RNN approach to investigate temporal dynamics in human EEG data in encoding WM load information.

Explore related subjects

q-bio.NC

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Samuel Goldstein, Zhenhong Hu, Mingzhou Ding. 2019-10-12. Decoding Working Memory Load from EEG with LSTM Networks. https://arxiv.org/abs/1910.05621

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Only what exists can cause: An intrinsic powers view of free will

This essay addresses the implications of integrated information theory (IIT) for free will. IIT is a theory of what consciousness is and of how its presence and quality can be accounted for in physical terms. According to IIT, the presence of consciousness is accounted for by a maximum of cause-effect power in the brain. Moreover, the way an experience feels is accounted for by how that cause-effect power is structured. If IIT is right, we do have free will in a genuine sense: we have alternatives, reasons, and values, we make decisions, and we-not our neurons or atoms-are the cause of our willed actions and bear responsibility for them. IIT's argument for genuine free will hinges on the proper understanding of consciousness as intrinsic existence, captured by its intrinsic powers ontology: what exists absolutely, in physical terms, are intrinsic entities, and only what exists can cause.

q-bio.NC↗

arXiv2026

Seeing the imagined: latent functional alignment in visual imagery decoding from fMRI data

Recent progress in visual brain decoding from fMRI has been enabled by large-scale datasets such as the Natural Scenes Dataset (NSD) and powerful diffusion-based generative models. While current pipelines are primarily optimized for perception, their performance under mental-imagery remains less well understood. In this work, we study how a state-of-the-art (SOTA) perception decoder (DynaDiff) can be adapted to reconstruct imagined content from the NSD-Imagery benchmark. We propose a latent functional alignment (LFA) approach that maps imagery-evoked activity to the pretrained model's semantic content-enriched conditioning space, by adding a simple alignment module, while keeping the original remaining components frozen. To mitigate the limited amount of matched imagery-perception supervision, we further introduce a neural retrieval-based augmentation strategy that selects semantically related NSD perception trials from the same participants. Across four subjects, LFA consistently improves high-level semantic reconstruction metrics relative to the frozen pretrained baseline and a voxel-space ridge alignment baseline, and enables above-chance decoding from multiple cortical regions. These results suggest that semantic structure learned from perception can be leveraged to stabilize and improve visual imagery decoding under out-of-distribution conditions.

q-bio.NC↗

arXiv2026

Deep Learning in Infant Functional Neuroimaging: Challenges, Advances, and Future Directions

Infancy is a critical developmental window characterized by rapid functional brain reorganization, during which large-scale networks emerge, individualized connectome signatures continue to form, and early deviations may shape long-term cognitive and clinical outcomes. Functional MRI (fMRI) offers an opportunity to study these processes in vivo, yet extracting developmentally meaningful information from it remains challenging due to comparatively short scan duration, structured motion artifacts, variable scan states, and rapid brain maturation. Amid these challenges, deep learning has expanded the capacity of computational neuroimaging by learning robust representations from noisy, high-dimensional data, integrating complex spatial and temporal information, and capturing the nonlinear and rapidly evolving organization of the developing brain. Here, we review recent advances in deep learning for infant functional neuroimaging, synthesizing progress across input representation formatting, population and individualized brain mapping, longitudinal trajectory forecasting, robust and explainable model evaluation, and biological translation. Collectively, these methodological advances mark a paradigm shift in infant functional neuroimaging from descriptive, group-level analyses toward reliable, individualized, and developmentally grounded models. Future progress will depend on larger and more diverse longitudinal datasets, developmentally appropriate model designs, rigorous and standardized evaluation, and integration of computational predictions with biological mechanisms towards clinically meaningful outcomes. Addressing these priorities will help establish deep learning as a robust framework for understanding early functional brain development, identifying developmental variation at the individual level, and ultimately supporting earlier and precise assessment of neurodevelopmental risk.

q-bio.NC↗