ROC & Precision–Recall Explorer
Connect a moving threshold to the confusion matrix, ROC space and the precision–recall curve.
Explore the labCOMPUTER VISION · DEEP LEARNING · EDUCATION
Exploring AI.
Learning through
practice.
I’m Ackley Will, a computer vision researcher and computing educator. I study how models learn and help people understand the ideas, evidence and code behind them.
BASED IN MICHIGAN · CONNECTED GLOBALLY
THE THREAD THROUGH MY WORKCuriosity. Clarity. Useful AI.
AT THE INTERSECTION
OF RESEARCH & PRACTICE
OF RESEARCH & PRACTICE
Computer visionDeep learningApplied AIAI education
A CONNECTED PRACTICE
From asking better questions
to building better models.
My work moves between research and teaching: studying how models behave, developing practical computer vision workflows, and helping people understand what their results mean. The goal is to connect technical depth with clear reasoning and useful applications.
A little more about meLEARN BY BUILDING
Your next step in AI.
AVAILABLE ON UDEMY
Computer Vision with PyTorch: Practical Deep Learning
Build a classifier. Understand its mistakes. Improve it with transfer learning. A practical path from your first model to a complete project.
VISUAL LEARNING
A small experiment.
A clearer idea.
Change one thing and follow what happens. 13 visual labs for curious minds and the classroom.
K-Means: Find the Groups
Place the centers, assign the points and update the means. Watch the groups emerge one step at a time.
Explore the labTransfer Learning: Choose What Learns
Freeze a real ResNet, choose the fine-tuning depth and see every trainable parameter. Turn your choices into PyTorch code.
Explore the labResNet: Inside the Residual Block
Open the stages of ResNet-18, 34 and 50. Follow tensor shapes, compare shortcuts and make the residual addition visible.
Explore the labData Augmentation: Build the Variations
Transform an image, generate a repeatable batch and inspect each crop, rotation and color adjustment. Decide what should stay invariant.
Explore the labRegularization: Learn Beyond the Sample
Train paired neural networks in your browser. Compare measured learning curves, validation errors and the predictions that remain.
Explore the labRESEARCH WITH PURPOSE
Better evidence.
More useful AI.
How much should we fine-tune? What changes when data is limited? My research explores computer vision and deep learning, with a focus on medical imaging, model evaluation, and accessibility.
Explore researchTransfer learningMedical imagingAssistive technology
SELECTED WORK
Ideas, put to work.
A closer look at the questions, methods, and experiments behind my work.
REFLECTIONS
Some lessons
stay with us.
A wrong phone number in London. A small coin behind a telephone booth. An adventure that went a little too far. Personal stories about faith, choices and finding perspective.
LET’S CONNECT
Research. Teaching. The next good question.
Interested in collaborating, learning, or sharing an idea? I’d like to hear from you.