CSC453

Hagan, M. T., Demuth, H. B., Beale, M. H., & De Jesús, O. (2014). Neural network design (2nd ed.). Martin Hagan.
These chapters introduce advanced optimization algorithms and cover foundational linear algebra necessary for understanding optimization surfaces and feature pipelines. The materials also provide initial context for feature extraction (CNN blocks) and lightweight deployment patterns, directly supporting all Module 4 MLOs and preparing you for the final assignments and exam.
Chapter 5 – Signal & Weight Vector Spaces (Inner Product, Norm, Orthogonality, Gram–Schmidt)
Chapter 6 – Linear Transformations (Change of Basis, Eigenvalues/Eigenvectors, Diagonalization)
Chapter 9 – Performance Optimization (Steepest Descent, Stable Learning Rates, Line Search, Newton, Conjugate Gradient)

TensorFlow. (n.d.). TensorFlow Playground. https://playground.tensorflow.org
An interactive visualization tool that lets users experiment with neural network configurations and see how models learn in real-time.

Nielsen, M. (n.d.). Neural networks and deep learning. http://neuralnetworksanddeeplearning.com
An accessible online book introducing the foundational concepts of neural networks, including perceptrons, backpropagation, and gradient descent.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, É. (2011). scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830. https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPClassifier.html
Documentation page for the MLPClassifier in scikit-learn, detailing parameters, examples, and implementation details for using multi-layer perceptrons in Python.