A Superficial Learning as an alternative to DeepLearning: A new approach

Bart Simpson

doi:10.36383/mach.v1i2sup.8

Articles

Vol. 1 No. 2sup (2022)

A Superficial Learning as an alternative to DeepLearning: A new approach

Bart Simpson^▸^▾

DOI: https://doi.org/10.36383/mach.v1i2sup.8
Submitted: April 18, 2023
Published: 2023-04-18

Abstract

In recent years, deep learning has dominated many areas of artificial intelligence due to its ability to model complex patterns in large datasets. However, deep learning systems often require massive computational resources, extensive labeled data, and long training times. This manuscript introduces Superficial Learning as an alternative paradigm that emphasizes simplicity, interpretability, and efficiency. Rather than relying on deeply layered neural architectures, superficial learning focuses on shallow models, lightweight feature transformations, and rapid training. This paper outlines the conceptual framework of superficial learning, discusses its advantages and limitations, and explores potential applications where it may outperform deep learning in terms of cost, speed, and interpretability.

References

1. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
2. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
3. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
4. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning. Springer.
5. Domingos, P. (2012). A few useful things to know about machine learning. Communications of the ACM.
6. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
7. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
8. Molnar, C. (2020). Interpretable Machine Learning. Lulu Press.
9. Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science.
10. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?” Explaining predictions of any classifier. KDD Conference.

[1] 1. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.

[2] 2. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.

[3] 3. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.

[4] 4. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning. Springer.

[5] 5. Domingos, P. (2012). A few useful things to know about machine learning. Communications of the ACM.

[6] 6. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

[7] 7. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.

[8] 8. Molnar, C. (2020). Interpretable Machine Learning. Lulu Press.

[9] 9. Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science.

[10] 10. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?” Explaining predictions of any classifier. KDD Conference.