Schedule - CS375 | CS 375-376 Spring 2026 at Calvin University

Week 1: Introduction

Getting started with ML: impacts of AI, running Python in notebooks, training an image classifier using off-the-shelf code.

Key Questions

What is the essence of modern approaches to AI?
What optimization games are AI systems playing?
Can AI systems be smarter than humans?

Objectives

Describe the goals of artificial intelligence and machine learning
Describe how learning-based AI learns from data, in contrast with rule-based (symbolic) AI
[OG-ProblemFraming-Paradigms]: Contrast supervised learning, self-supervised learning, and reinforcement learning
Write and execute basic Python code using Jupyter Notebooks

Wednesday

Welcome discussion: hopes and concerns
Course logistics
- Assessments: skills, effort, and community
- Weekly journals, quizzes every other Friday
- Perusall
Slides: Welcome to CS 375
- My story and stance:
  - how God brought me to learn about ML/AI
  - how it’s a gift that will definitely be in the new creation but we abuse it
- We need to work to discern AI together.
  - Importance
    - Divisiveness
    - Economic impacts
    - Existential angst
    - Identity, desires, and relationships
    - You need to be able to discern it fundamentally, not just from external behavior
  - This class:
    - This class will be about how it works at a fundamental level and what that fundamental understanding helps us understand about how it fits into God’s story
- Tweakable Machines playing Optimization Games
  - board games
  - hook-the-human games
  - predict protein folding, guess the weather, design a molecule, …
  - imitation games: mimicking decisions, conversations, images, …
  - exploration games: control a robot, …
- Problem framing
  - programmed vs learned
  - supervised learning: mimicry
  - self-supervised learning: reducing surprise
  - reinforcement learning: learning by trial and error

Friday

Lab 1

Recording

Week 2: Array Programming & Regression

Introduction to numerical computing with NumPy/PyTorch: element-wise operations, reductions, dot products, MSE. First taste of sklearn regression.

Key Questions

How do we represent data as arrays/tensors?
What is a dot product and how is it used in ML?
What does it mean to “fit” a model?

Objectives

This week we’ll make progress towards the following objectives:

[TM-TensorOps]: Implement basic array-computing operations (element-wise operations, reductions, dot products)
[OG-LossFunctions]: Compute MSE loss
[OG-ProblemFraming-Paradigms]: Contrast different types of learning machines (supervised learning, unsupervised learning, RL)
If you didn’t take DATA 202: use the sklearn API for basic regression tasks

Resources

Additionally, you may find these interactive articles helpful (by Amazon’s Machine Learning team):

Linear Regression (originally by Amazon Web Services, some edits by Prof Arnold)

Monday

Assumptions of AI: Experience (“IID” amnesia vs continual life; our mistakes matter but Jesus gives us grace)
Handout: Lab 1 review, intro to dot product
Lab 1 review
Intro to dot product

Wednesday

Handout: Supervised Learning
Slides: CS 375 Week 2
- Landscape of AI/ML (supervised, unsupervised, RL)

Friday

Handout: Problem framing, dot products review, Lab notes
Lab 2
- Notebook: PyTorch Warmup (name: u02n1-pytorch.ipynb; show preview, open in Colab)
Intro to array programming, regression losses
If time:
- Notebook: Regression in scikit-learn (name: u02n2-sklearn-regression.ipynb; show preview, open in Colab)

Week 3: Linear Models for Regression and Classification (and LLM APIs)

Linear regression and classification from the ground up. Introduction to classification models and metrics. If time: Using LLM APIs to build AI-powered applications.

Key Questions

How is linear regression an optimization game played by a tuneable machine?
How do we call an LLM API?
How do we evaluate a classification model?

Objectives

[TM-LinearLayers]: Fit a linear regression model “by hand” using numerical computing primitives
[OG-ProblemFraming-Supervised]: Identify regression vs classification tasks and select appropriate loss functions
[OG-LossFunctions]: Compute and interpret cross-entropy loss
[OG-LLM-APIs]: Use an LLM API to build an AI-powered application

Monday

Handout: PyTorch, dot products, regression metrics
Assumptions of AI: What’s the objective?
- ML: optimize single numbers at huge scale
- Reality:
  - " The thief comes only to steal and kill and destroy; I have come that they may have life, and have it to the full." (John 10:10)
  - the objective is life
    - Many wise paths
    - passing on good to children (unbounded richness)
Logistics:
- Homework 1
- Journals
- Quiz opportunity on Wednesday
Slides: CS 375 Week 3
Lab recap: PyTorch (and sklearn notebooks)

Wednesday

First quiz opportunity [OG-ProblemFraming-Paradigms], [OG-ProblemFraming-Supervised], [TM-DotProduct], [OG-LossFunctions], [TM-TensorOps]
Starting “Linear Regression the Hard Way”
- Building intuition for linear regression using UDL figure or linreg explainer
Notebook: Linear Regression the Hard Way (name: u03n1-linreg-manual.ipynb; show preview, open in Colab)

Friday

Tech update: Opus 4.6 release
Handout: Matrix product, Elo intuition
Slides: CS 375 Week 3
Reviewing notebooks:
- Notebook: Train a simple image classifier (name: u01n1-train-clf.ipynb; show preview, open in Colab)
(we didn’t get to…)
- Notebook: PyTorch Warmup (name: u02n1-pytorch.ipynb; show preview, open in Colab)
- Notebook: Linear Regression the Hard Way (name: u03n1-linreg-manual.ipynb; show preview, open in Colab)
- Notebook: Regression in scikit-learn (name: u02n2-sklearn-regression.ipynb; show preview, open in Colab)
- Notebook: Classification in scikit-learn (name: u03n2-sklearn-classification.ipynb; show preview, open in Colab)

Week 4: Multi-input Models & Softmax

Extending linear models to multiple inputs. Understanding softmax and cross-entropy loss.

Key Questions

How does linear regression extend to multiple input features?
What is softmax and why do we use it for classification?
What is cross-entropy loss?

Objectives

[TM-TensorOps]: Work with multi-dimensional tensors, predict shapes of matrix operations
[TM-DataFlow]: Trace data shapes through a multi-input linear model
[TM-Softmax]: Implement softmax and explain why it produces a valid probability distribution
[OG-LossFunctions]: Describe and compute cross-entropy loss

Monday

Classification metrics (accuracy, cross-entropy)
Context discussion: AI fairness and bias
LLM API intro: “use an AI to make an AI”
Notebook: Multiple Linear Regression, the Hard Way (name: u04n1-multi-linreg-manual.ipynb; show preview, open in Colab)

Wednesday

Slides: Computing
Notebook: Softmax, part 1 (name: u04n2-softmax.ipynb; show preview, open in Colab)
Interactive softmax demo

Friday

Handout
- gradient intuition: suppose a dot b is 0. How can we change each element of b (in isolation) to make the dot product 0.1 instead?
Notebook: From Linear Regression in NumPy to Logistic Regression in PyTorch (name: u04n3-logreg-pytorch.ipynb; show preview, open in Colab)
Hw2 soft-due: demo an AI-powered application

Week 5: Features & MLP Architecture

Understanding feature extraction with ReLU. Introduction to classifier heads and bodies. The multi-layer perceptron (MLP) architecture.

Key Questions

Why are good features important for neural networks?
What is a classifier “head” vs “body”?
How does ReLU create useful features?

Objectives

[TM-RepresentationLearning]: Explain why good features make classification easier
[TM-ActivationFunctions]: Implement ReLU and explain what it does
[TM-DataFlow]: Trace the data flow through an MLP, labeling shapes at each layer
[TM-MLPParts]: Identify and explain the components of an MLP (linear layers, activations, output layer)

Monday

Feature extractors intro
ReLU features intro
Classifier head and body intro

Wednesday

Notebook: ReLU Regression Interactive (name: u05n00-relu.ipynb; show preview, open in Colab)
Notebook: Logistic Regression and MLP (name: u05n2-logreg-mlp.ipynb; show preview, open in Colab)
MLP shapes practice

Friday

Preview of learning by gradient descent
Review day: gradient game
Tech presentation

Week 6: Gradient Descent & Generalization

Learning by gradient descent. Understanding why generalization matters and how to measure/improve it.

Key Questions

How does gradient descent work?
What is overfitting vs underfitting?
How can data augmentation help generalization?

Objectives

[TM-Implement-TrainingLoop]: Train an MLP classifier by gradient descent and understand each step
[OG-Theory-SGD]: Describe how SGD uses gradients and batches to improve performance
[TM-Autograd]: Explain what loss.backward() and optimizer.step() do
[OG-Generalization]: Diagnose overfitting and underfitting from learning curves
[OG-DataDistribution]: Explain how data augmentation expands the effective training distribution
[OG-Implement-Validate]: Explain the importance of evaluating models on unseen data

Monday

Gradient game activity
Notebook: MNIST with PyTorch (name: u06n1-mnist-torch.ipynb; show preview, open in Colab)

Wednesday

Notebook: Compute gradients using PyTorch (name: u06n2-compute-grad-pytorch.ipynb; show preview, open in Colab)
Review training loops, SGD, MLP model

Friday

Will It Generalize? slides
Data augmentation notebook
Tech presentation

Week 7: Embeddings & RL

Embeddings as the data structures of neural computation. Introduction to reinforcement learning.

Key Questions

What are embeddings and how are they used in ML?
How does reinforcement learning differ from supervised learning?
What is the difference between learning to mimic vs learning by exploring?

Objectives

[TM-Embeddings]: Explain what embeddings are and how they represent similarity
[OG-Pretrained]: Explain how a pretrained model can be repurposed using the body + head pattern
[OG-ProblemFraming-Paradigms]: Contrast supervised learning and reinforcement learning
[OG-DataDistribution]: Contrast how data distribution is given (supervised) vs shaped by exploration (RL)

Monday

Embeddings Day: words, sentences, images
Slides: Computing
Notebook: Probe an Image Classifier (name: u07n1-image-embeddings.ipynb; show preview, open in Colab)

Wednesday

Reinforcement Learning intro
Notebook: A Reinforcement Learning Example (name: u07n2-rl.ipynb; show preview, open in Colab)
Optional: Notebook: u07n1-image-ops.ipynb

Friday

Slides: CS 375: Wrap-Up
Learning to Mimic vs Learning by Exploring
Course wrap-up