Episodic memory recognition of the hippocampus using a deep learning method

Takashi Kuremoto, Takaaki Sasaki, Junko Ishikawa, Shingo Mabu, Dai Mitsushima


Hippocampus plays an important role in processing episodic memory. The different patterns of multi-unit activity (MUA) of CA1 neurons in hippocampus corresponds to the different high order functions of the brain such as memory, association, planning, action decision, etc. In this paper, a deep learning model, which is a composition of convolutional neural network (CNN) and support vector machine (SVM), is adopted to classify 4 kinds of episodic memories of a male rat: restraint stress (restraint), contact with a female rat (female), contact with a male rat (male), and contact with a novel object (object). In addition, the characteristic patterns of the different events occurred in CA1 neurons are specified by the feature explanation of CNN using Grad-CAM. As the result, this study suggests that it is available to recognize episodic memories by MUA signals and vice versa.


episodic memory, multiple-unit firing activity (MUA), deep learning, convolutional neural network (CNN), support vector machine (SVM)


Buzsaki, G. Hippocampal sharp wave- ripple: A cognitive biomarker for episodic memory and planning. Hippocampus, 25, pp. 1073-1188 (2015)

Joo, H. R., Frank, L.M. The hippocampal sharp wave-ripple in memory retrieval for immediate use and consolidation. Nature Reviews Neuroscience, 19, pp. 744-757 (2018)

Kay, K., Frank, L.M. Three brain states in the hippocampus and cortex. Hippocampus, 29, pp. 184-238 (2019)

Fenandez-Ruiz, A., et al. Long-duration hippocampal sharp wave ripples improve memory. Science, 264, pp. 1082-1086 (2019)

Ishikawa, J., Tomokage, T., Mitsushima, D. A possible coding for experience: ripple-like events and synaptic diversity, BioRxiv: https://doi.org/10.1101/2019.12.30.891259, (2019)

Selvaraju R. R., et al. Grad-CAM: Explanations from Deep Networks via Gradient-based Localization, arXiv:1610.02391v4 [cs.CV] (2019)

Blankertz, B., et al. The BCI Competition 2003: Progress and perspectives in detection and discrimination of EEG Single Trials. IEEE Transaction on Biomedical Engineering, 51(6), 1044-1051 (2004)

Chin, Z. Y., Ang, K. K., Wang, C., Guan, C., and Zhang, H. Multi-class filter bank common spatial pattern for four-class motor imagery BCI. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2009. EMBC 2009, 571–574 (2009)

Kuremoto, T., Baba, Y., Obayashi, M., Mabu, S., Kobayashi, K. Enhancing EEG signals recognition using ROC curve, Journal of Robotics, Networking and Artificial Life, 4(4), 283-286 (2018)

Kuremoto, T., Baba, Y., Obayashi, M., Mabu, S., Kobayashi, K., Mental task recognition by EEG signals: A novel approach with ROC analysis, In Human-Robot Interaction –Theory and Application (eds. Anbarjafari, G., Escalera, S.), Chapter 4, 65-78, InTech (2018)

Tang, Z., Li, C., Sun, S. Single-trial EEG classification of motor imagery using deep convolutional neural networks, Optik, 130, 11-18 (2017)

Schirrmeister, R.T., et al. Deep learning with convolutional neural networks for EEG decoding and visualization, arXiv:1703.05051v5 [cs.LG] (2018)

Kuremoto, T., Sasaki, T., Mabu, S. Mental task recognition using EEG signal and deep learning methods, Stress Brain and Behavior, Vol. 1, pp.18-23 (2019)

Colorado State University, Brain-Computer Interfaces Laboratory: http://www.cs.colostate.edu/eeg/

BCI competition II: http://www.bbci.de/competition/ii/#datasets

Mitsushima, D., Ishihara, K., Sano, A., Kessels, H.W., Takahashi, T. Contextual learning requires synaptic AMPA receptor delivery in the hippocampus. Proceedings of the National Academy of Sciences of the United States of America, 108, pp. 12503-12508 (2011)

DOI: http://dx.doi.org/10.18103/imr.v7i1.915


  • There are currently no refbacks.
Copyright 2016. All rights reserved.