AAI_2025_Capstone_Chronicles_Combined

7.) References

AstroDave and Will Cukierski. Digit Recognizer .

https://kaggle.com/competitions/digit-recognizer, 2012. Kaggle. Google Research. (2024). jax.vmap . JAX Documentation. Retrieved March 24, 2025, from https://docs.jax.dev/en/latest/_autosummary/jax.vmap.html Kaplan, J., McCandlish, S., Henighan, T., Brown, T., Chess, B., Child, R., Gray, S., Radford, A., & Amodei, D. (2020). Scaling laws for neural language models . arXiv preprint arXiv:2001.08361. https://arxiv.org/abs/2001.08361 Keskar, N., Mudigere, D., Nocedal, J., Smelyanskiy, M., & Tang, P. (2017). On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima . ArXiv, abs/1609.04836. Lobacheva, E., Chirkova, N., Kodryan, M., & Vetrov, D. (2020). On power laws in deep ensembles. Advances in Neural Information Processing Systems, 33, 1–12. Retrieved from https://papers.neurips.cc/paper_files/paper/2020/file/191595dc11b4d6e54f01504e3aa92f96-Paper. pdf Nazary, A. (n.d.). Stockdex: Python package to extract and plot financial data [Computer software]. GitHub. https://github.com/ahnazary/stockdex Pedregosa, F., et al. (2011). Scikit-learn: Machine learning in Python [Preprint]. arXiv. https://arxiv.org/abs/1201.0490 Sergeev, A., & Del Balso, M. (2018). Horovod: fast and easy distributed deep learning in TensorFlow . arXiv. https://arxiv.org/abs/1802.05799 Whitney, W. (2021). Parallelizing neural networks on one GPU with JAX . Will Whitney's Blog. https://willwhitney.com/parallel-training-jax.html Yi, X. (2024). A study of performance programming of CPU, GPU accelerated computers and SIMD architecture. arXiv. https://doi.org/10.48550/arXiv.2409.10661

Note: Some writing and references were refined with guidance from an AI chat assistant. Any errors remain the responsibility of the author.

145