Preprint / Version 1

Determining the Optimal Model, Reaction Time Delay, and Preprocessing Technique for the Classification of Visual Stimuli from Mouse Visual Cortex Activity


  • Harjaisal Brar Stockdale High School



machine learning, computational neuroscience, visual cortex, preprocessing, reaction time offset, visual stimulus, model, allen institute, classifier, mouse model, scikit, solvers, kernels, logistic regression, multilayer perceptron, mlp, svm, support vector machine


Improving classification accuracies of visual stimuli from neural data is important in developing future models, including those for transfer learning, which will allow further research in the areas of visual process and vision loss. In this paper, several models and solvers/kernels, time delays, and preprocessing techniques are tested. This study finds several parameters that can be used to maximize prediction accuracy, ultimately producing an average accuracy of 81% when evaluated on the test set.


Allen SDK. (n.d.). Allen SDK Dev Documentation. Retrieved April 19, 2023, from

Andrade, C. (2021). Z Scores, Standard Scores, and Composite Test Scores Explained. Indian Journal of Psychological Medicine, 6, 555–557.

Barboza, F., Kimura, H., & Altman, E. (2017). Machine learning models and bankruptcy prediction. Expert Systems with Applications, 405–417.

Boashash, B. (2016). Time-Frequency Signal Analysis and Processing (2nd ed., pp. 521–573). Academic Press.

Cho, J. H., & Lee, H. (2020). Optimization of Machine Learning in Various Situations Using ICT-Based TVOC Sensors. Micromachines.

Day, O., & Khoshgoftaar, T. (2017). A survey on heterogeneous transfer learning. Journal of Big Data.

Gherardi, M. (2021). Solvable Model for the Linear Separability of Structured Data. Entropy, 3, 305.

Iqbal, A., Dong, P., Kim, C. M., & Jang, H. (2019). Decoding Neural Responses in Mouse Visual Cortex through a Deep Neural Network. ArXiv.

Jain, A., Bansal, R., Kumar, A., & Singh, K. (2015). A comparative study of visual and auditory reaction times on the basis of gender and physical activity levels of medical first year students. International Journal of Applied and Basic Medical Research, 2, 124.

Kindel, W. F., Christensen, E. D., & Zylberberg, J. (2019). Using deep learning to probe the neural code for images in primary visual cortex. Journal of Vision, 4, 29.

López, O. A. M., López, A. M., & Crossa, J. (2022). Multivariate Statistical Machine Learning Methods for Genomic Prediction (pp. 109–139). Springer Nature.

Ranjbarzadeh, R., Jafarzadeh Ghoushchi, S., Bendechache, M., Amirabadi, A., Ab Rahman, M. N., Baseri Saadi, S., Aghamohammadi, A., & Kooshki Forooshani, M. (2021). Lung Infection Segmentation for COVID-19 Pneumonia Based on a Cascade Convolutional Network from CT Images. BioMed Research International, 1–16.

scikit-learn. (n.d.). Scikit-Learn 0.16.1 Documentation. Retrieved April 19, 2023, from

Shmiel, T., Drori, R., Shmiel, O., Ben-Shaul, Y., Nadasdy, Z., Shemesh, M., Teicher, M., & Abeles, M. (2005). Neurons of the cerebral cortex exhibit precise interspike timing in correspondence to behavior. Proceedings of the National Academy of Sciences, 51, 18655–18657.

Talboom, J. S., De Both, M. D., Naymik, M. A., Schmidt, A. M., Lewis, C. R., Jepsen, W. M., Håberg, A. K., Rundek, T., Levin, B. E., Hoscheidt, S., Bolla, Y., Brinton, R. D., Schork, N. J., Hay, M., Barnes, C. A., Glisky, E., Ryan, L., & Huentelman, M. J. (2021). Two separate, large cohorts reveal potential modifiers of age-associated variation in visual reaction time performance. Npj Aging, 1.

Tanaka, T., Nambu, I., Maruyama, Y., & Wada, Y. (2022). Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography. Sensors, 13, 5005.

Vaux, D. L., Fidler, F., & Cumming, G. (2012). Replicates and repeats—what is the difference and is it significant? EMBO Reports, 4, 291–296.

Visual Coding - Neuropixels. (n.d.). Brain Map. Retrieved April 19, 2023, from

Zhou, Z., Shin, J., Zhang, L., Gurudu, S., Gotway, M., & Liang, J. (2017). Fine-tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit.