Skip to content

References: Neural Networks and MNIST

  1. Neural Network — Wikipedia https://en.wikipedia.org/wiki/Neural_network_(machine_learning) Covers the foundational concepts of artificial neural networks, including how layers of nodes process information, what activation functions do, and how networks learn from data — the theoretical backbone of this chapter.

  2. MNIST Database — Wikipedia https://en.wikipedia.org/wiki/MNIST_database Describes the MNIST dataset of 70,000 handwritten digit images used as the classic benchmark for image classification. Explains the dataset's origin, structure, and why it became the "Hello, World" of deep learning.

  3. Deep Learning — Wikipedia https://en.wikipedia.org/wiki/Deep_learning Explains deep learning as a branch of machine learning that uses multi-layer neural networks to recognize patterns. Directly relevant to understanding why stacking layers in Keras gives the model its power to recognize digits.

  4. Python Crash Course by Eric Matthes (No Starch Press) A beginner-friendly introduction to Python that builds the programming fundamentals — functions, loops, lists, and libraries — needed before working with Keras and training a neural network on real data.

  5. Python for Kids by Jason R. Briggs (No Starch Press) Introduces Python concepts through playful, approachable examples suited to ages 10–13. Provides the core Python syntax and data-structure knowledge that underpins loading the MNIST dataset and writing training loops in Keras.

  6. Real Python — Neural Networks with Keras https://realpython.com/python-keras-text-classification/ A practical, step-by-step guide to building classification models with Keras in Python. Demonstrates how to define layers, choose activation functions, compile a model, and evaluate accuracy — all central skills in this chapter.

  7. GeeksforGeeks — Deep Learning with Python https://www.geeksforgeeks.org/deep-learning-with-python/ Covers deep learning concepts and Keras workflows with clear code examples. Helpful for understanding how to build, train, and test a neural network layer by layer, reinforcing the hands-on work in this chapter.

  8. W3Schools — Python Machine Learning https://www.w3schools.com/python/python_ml_getting_started.asp A gentle introduction to machine learning with Python, including key vocabulary such as training data, features, and model evaluation. Useful for students who want a plain-language explanation alongside this chapter's code.

  9. Programiz — Python NumPy Tutorial https://www.programiz.com/python-programming/numpy Introduces NumPy arrays, which are the underlying data structure for MNIST images in Keras. Understanding array shapes, indexing, and reshaping is essential for preprocessing digit images before feeding them into a neural network.

  10. Khan Academy — Intro to Neural Networks https://www.khanacademy.org/computing/intro-to-python-fundamentals Offers beginner-friendly computing lessons that build intuition for how programs learn from data. Supports students who want additional background on computational thinking before diving into training and evaluating models in Keras.