# Deep Neural Imputation: A Framework for Recovering Incomplete Brain Recordings

arXiv: https://arxiv.org/abs/2206.08094 · HTML: https://mlsanity.com/paper/2206.08094/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 39 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [MaskGAN: Better Text Generation via Filling in the______](https://mlsanity.com/paper/1801.07736/) (2018)
- [NAOMI: Non-Autoregressive Multiresolution Sequence Imputation](https://mlsanity.com/paper/1901.10946/) (2019)
- [Hierarchical Optimal Transport for Multimodal Distribution Alignment](https://mlsanity.com/paper/1906.11768/) (2019)
- [On the Benefits of Early Fusion in Multimodal Representation Learning](https://mlsanity.com/paper/2011.07191/) (2020)
- [Variable-rate discrete representation learning](https://mlsanity.com/paper/2103.06089/) (2021)
- [Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding](https://mlsanity.com/paper/1705.08006/) (2017)
- [AJILE Movement Prediction: Multimodal Deep Learning for Natural Human Neural Recordings and Video](https://mlsanity.com/paper/1709.05939/) (2017)
- [Mutual Information in Frequency and its Application to Measure Cross-Frequency Coupling in Epilepsy](https://mlsanity.com/paper/1711.01629/) (2017)

## Built on by (most cited first, 5 of 5)

- [TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis](https://mlsanity.com/paper/2402.16412/) (2024)
- [Population Transformer: Learning Population-level Representations of Neural Activity](https://mlsanity.com/paper/2406.03044/) (2024)
- [Generalizability Under Sensor Failure: Tokenization + Transformers Enable More Robust Latent Spaces](https://mlsanity.com/paper/2402.18546/) (2024)
- [Imputing Brain Measurements Across Data Sets via Graph Neural Networks](https://mlsanity.com/paper/2308.09907/) (2023)
- [Inference of Unknown Dynamical Components Using Next Generation Reservoir Computing: From Chaotic Systems to Climate Data](https://mlsanity.com/paper/2609.24754/) (2026)

## Abstract (arXiv)

Neuroscientists and neuroengineers have long relied on multielectrode neural recordings to study the brain. However, in a typical experiment, many factors corrupt neural recordings from individual electrodes, including electrical noise, movement artifacts, and faulty manufacturing. Currently, common practice is to discard these corrupted recordings, reducing already limited data that is difficult to collect. To address this challenge, we propose Deep Neural Imputation (DNI), a framework to recover missing values from electrodes by learning from data collected across spatial locations, days, and participants. We explore our framework with a linear nearest-neighbor approach and two deep generative autoencoders, demonstrating DNI's flexibility. One deep autoencoder models participants individually, while the other extends this architecture to model many participants jointly. We evaluate our models across 12 human participants implanted with multielectrode intracranial electrocorticography arrays; participants had no explicit task and behaved naturally across hundreds of recording hours. We show that DNI recovers not only time series but also frequency content, and further establish DNI's practical value by recovering significant performance on a scientifically-relevant downstream neural decoding task.