This is a list of course materials. I will post new files and website links as we progress through the course.
Sjöberg and Ljung 1995 -- week 9 - Sjöberg, J. and Ljung, L. (1995), “Overtraining, Regularization and Searching for a Minimum, with Application to Neural Networks,” International Journal of Control, vol. 62(6), pp. 1391–1407.
Schulman, J. et al. (2016)--week 13 on RL - Schulman, J. et al. (2016), "High-Dimensional Continuous Control Using Generalized Advantage Estimation," 9 Sep 2016 (v5), https://arxiv.org/abs/1506.02438.
Poggio et al. Deep Networks Avoid Curse of Dimensionality - Tomaso Poggio, Hrushikesh Mhaskar, Lorenzo Rosasco, Brando Miranda, Qianli Liao (2017), "Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review," arXiv:1611.00740. There is also a "reader-friendly" discussion about this paper, titled "Plumbing the Depths of Neural Nets," at the MIT Spectrum newsletter (https://spectrum.mit.edu/winter-2018/plumbing-the-depths-of-neural-nets/).
Week 4: Geman, S., Bienenstock, E., and Doursat, R. (1992), “Neural Networks and the Bias/Variance Dilemma,” Neural Computation, vol. 4, pp. 1–58. http://web.mit.edu/6.435/www/Geman92.pdf
Online course in RL - Online course by David Silver in RL. Useful for week 13 topic. See especially Lecture 7.
Lillicrap, T. P. et al. (2016)--week 13 reading on RL - Lillicrap, T. P. et al. (2016),"Continuous control with deep reinforcement learning, 29 Feb 2016 (v5), https://arxiv.org/abs/1509.02971.
Week 7: Thompson, N. C., Greenewald, K., Lee, K., and Manso, G. F., "Deep Learning's Diminishing Returns: The Cost of Improvement is Becoming Unsustainable," in IEEE Spectrum, vol. 58, no. 10, pp. 50–55, October 2021, http://dx.doi.org/10.1109/MSPEC.2021.9563954.
Week 8: Kulkarni, S. R., Lugosi, G., and Venkatesh, S. S. (1998), “Learning Pattern Classification—A Survey,” IEEE Transactions on Information Theory, vol. 44(6), pp. 2178–2206. http://dx.doi.org/10.1109/18.720536
Deep learning week 2: Deng and Yu (2014) - Reading for week 7: Deng, L. and Yu, D. (2014), “Deep Learning: Methods and Applications,” Foundations and Trends in Signal Processing, vol. 7, no. 3–4, pp 197–387.
Deep learning week 1: Bengio et al. - Reading for weeks 6 - 7: Bengio, Y., LeCun, Y., and Hinton, G. (2015), “Deep Learning,” Nature, vol. 521, pp. 436–444.
Week 9: Ang et al. (2005) - Ang, K. H., Chong, G. C. Y., and Li, Y. (2005), “PID Control System Analysis, Design, and Technology,” IEEE Transactions on Control Systems Technology, vol. 13(4), pp. 559–576.
Week 10: Three readings as follows:
Spall, J. C. (1988), “An Overview of Key Developments in Dynamic Modeling and Estimation,” in Bayesian Analysis of Time Series and Dynamic Models (J. C. Spall, ed.), Marcel Dekker, New York, pp. xv–xxvii. (General introduction/historical review; paper posted below as BayesAnalTimeSerDynModel88_KalmanIntro.pdf.)
Simon, D. (2006), Optimal State Estimation: Kalman, H∞, and Nonlinear Approaches, Wiley. (Main reading for week 10. Focus on Chapter 5; book is accessible through JHU library.)
Shin Wakitani, Hiroki Nakanishi, Yoichiro Ashida, Toru Yamamoto, "Study on a Kalman Filter based PID Controller," IFAC-PapersOnLine, Volume 51, Issue 4, 2018, Pages 422-425, https://doi.org/10.1016/j.ifacol.2018.06.131. (Example that connects themes of weeks 9 and 10 for the class.)
Week 11: Main reading is: Narendra, K. S. and Parthasarathy, K. (1990), “Identification and Control of Dynamical Systems Using Neural Networks,” IEEE Transactions on Neural Networks, vol. 1, pp. 4-27, https://doi.org/10.1109/72.80202. (There are also many other recent papers, but most follow the same general framework.)
Week 12: Main reading is: Spall, J. C. and Cristion, J. A. (1998), “Model-Free Control of Nonlinear Stochastic Systems with Discrete-Time Measurements,” IEEE Transactions on Automatic Control, vol. 43, pp. 1198–1210, .http://dx.doi.org/10.1109/9.718605
Week 13: Main reading is: Brunton, S. L. and Kutz, H. N. (2019), Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control (1st. ed.), Chapter 11, “Reinforcement Learning,” Cambridge University Press, USA. Chapter is available below.