DDS-7250

IEEE Innovation at Work. (n.d.). What is ‘causal inference’ and why is it key to machine learning? Retrieved from https://innovationatwork.ieee.org/what-is-causal-inference-and-why-is-it-key-to-machine-learning/

This article explores the concept of causal inference, its importance in understanding cause-and-effect relationships, and its critical role in advancing machine learning applications.

Linden, A., & Adams, J. L. (2012). Combining the regression discontinuity design and propensity score-based weighting to improve causal inference in program evaluation. Journal of Evaluation in Clinical Practice, 18(2), 317–325. https://doi.org/10.1111/j.1365-2753.2011.01768.x

This article presents a hybrid methodology combining regression discontinuity design and propensity score-based weighting to enhance causal inference in program evaluations.

Rosenbaum, P. R. (2023). 6 quasi-experimental devices in the design of observational studies. P. 103–115.
https://search.ebscohost.com/login.aspx?direct=true&AuthType=sso&db=edseee&AN=edseee.10103859&site=eds-live&scope=site&custid=natuniv

This chapter explores quasi-experimental methodologies to strengthen causal inference in observational studies.

Scherbakov, D., Hubig, N., Jansari, V., Bakumenko, A., & Lenert, L. A. (2024).
https://search.ebscohost.com/login.aspx?direct=true&AuthType=sso&db=edsarx&AN=edsarx.2409.04600&site=eds-live&scope=site&custid=natuniv

This paper investigates the use of Large Language Models for automating systematic literature reviews, highlighting their advantages and limitations.

Fatima, N., Imran, A. S., Kastrati, Z., Daudpota, S. M., & Soomro, A. (2022). A systematic literature review on text generation using deep neural network models. IEEE Access, 10, 53490–53503. https://doi.org/10.1109/ACCESS.2022.3174108

This study provides a comprehensive review of deep neural network models for text generation, discussing methodologies, challenges, and advancements.

Sayed, R., Azmi, H., Shawkey, H., Khalil, A. H., & Refky, M. (2023). A systematic literature review on binary neural networks. IEEE Access, 11, 27546–27578. https://doi.org/10.1109/ACCESS.2023.3258360

This article reviews the state-of-the-art in binary neural networks, including their architectures, training methods, and real-world applications.

Series Forecasting and Classification
Corradini, F., Gori, M., Lucheroni, C., Piangerelli, M., & Zannotti, M. (2024).
https://search.ebscohost.com/login.aspx?direct=true&AuthType=sso&db=edsarx&AN=edsarx.2410.22377&site=eds-live&scope=site&custid=natuniv

This paper systematically reviews spatio-temporal graph neural networks for time series forecasting and classification, emphasizing their capabilities and limitations.

Miikkulainen, R. (2024). Evolution of neural networks. In Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO '24 Companion), 928–945. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3638530.3648407

This work explores the evolution of neural networks through genetic and evolutionary computation, highlighting innovations in architecture design and optimization.

Mori, H., Kawano, K., & Yokoyama, H. (2017). Causal patterns: Extraction of multiple causal relationships by mixture of probabilistic partial canonical correlation analysis. 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 744–754. https://doi.org/10.1109/DSAA.2017.60

This paper presents a novel method for extracting multiple causal relationships using probabilistic partial canonical correlation analysis.