Flashcards · Machine Learning · Free
Machine Learning flashcards, generated for you.
Example Machine Learning study cards to learn from right now — then generate a full set from your own notes (plus a practice quiz) and export to Quizlet or Anki. Free, no account needed.
Example Machine Learning flashcards
What is machine learning at its core?
A computer system that learns patterns from data and makes predictions or decisions without being explicitly programmed for each case.
Why do we need machine learning instead of writing rules manually?
Patterns in real-world data are too complex or numerous to code by hand. ML systems can discover these patterns automatically from examples.
What's the key difference between supervised and unsupervised learning?
Supervised learning: we have labeled examples (input + correct answer) to learn from. Unsupervised learning: we only have inputs and must find hidden patterns ourselves.
What does a training set do?
Provides example data (inputs and outputs) that the model learns from to discover patterns and adjust its internal parameters.
Why do we need a separate test set?
To measure how well the model generalizes to new, unseen data. Testing on training data gives falsely high accuracy (overfitting).
What is overfitting in intuitive terms?
The model memorizes noise and quirks in training data instead of learning true patterns, so it fails on new data. Like memorizing exam answers instead of understanding concepts.
How does a linear regression model make predictions mathematically?
It computes: y = mx + b (or y = w₁x₁ + w₂x₂ + ... + b for multiple features). It finds weights (m, w) and bias (b) that minimize prediction error on training data.
What does 'loss function' mean?
A mathematical measure of how wrong the model's predictions are. Lower loss = better fit. The model adjusts parameters to minimize loss on training data.
What is a decision tree and why is it interpretable?
A model that makes predictions by asking yes/no questions about features in a tree structure. It's interpretable because you can see and explain the exact decision path taken.
What is gradient descent and what problem does it solve?
An optimization algorithm that iteratively adjusts model parameters in small steps to reduce loss. It solves the problem of finding which weights minimize prediction error when there are too many possibilities to check manually.
Make your own Machine Learning study set
Flashcards for related topics
Studying Machine Learning to build with AI? MindloomHQ turns it into real skills — structured courses, agent projects, and certificates.
Explore MindloomHQ →