Machine Learning flashcards that match how you actually study
Whether you are prepping for exams or building long-term knowledge, Machine Learning rewards retrieval practice—not rereading. NoteFren converts your handwritten notes, slides, and PDF text into clean Q&A flashcards so you can review Machine Learning with spaced repetition in minutes, not hours.
Studying Machine Learning with flashcards
Machine learning builds systems that learn patterns from data rather than following hand-coded rules, spanning supervised, unsupervised, and reinforcement learning. The field blends statistics, linear algebra, and optimization with practical concerns like data cleaning and evaluation. Students struggle with the conceptual glue: understanding the bias-variance tradeoff, why a model overfits, what a loss function actually optimizes, and how gradient descent updates parameters. Terminology overload is real, and it is easy to memorize algorithm names without grasping when each is appropriate or how its hyperparameters change behavior.
Active recall works well because ML is a landscape of algorithms, each with assumptions, strengths, and failure modes you must recall on demand. Spaced repetition keeps the definitions, evaluation metrics, and the intuition behind each method fresh. Build cards that pair an algorithm with the problem type it solves and its key assumption ("logistic regression → binary classification, linear decision boundary"). Card each metric with when it matters — precision versus recall when classes are imbalanced. Card the shape of the bias-variance curve. If you sketch a computational graph or a decision boundary in NoteFren, turn it into a prompt and quiz yourself on how a hyperparameter shifts it rather than just naming the algorithm.
Key topics to turn into flashcards
Supervised versus unsupervised learning
Card the distinction between labeled and unlabeled data and which tasks (classification, regression, clustering, dimensionality reduction) fall under each.
Loss functions and gradient descent
Test what MSE and cross-entropy penalize and how the learning rate and gradient direction update parameters each step.
Bias-variance tradeoff and regularization
Put the signs of underfitting versus overfitting and how L1 and L2 regularization constrain a model on cards.
Core algorithms
Quiz the assumptions and use cases of linear and logistic regression, decision trees, k-nearest neighbors, and support vector machines.
Evaluation metrics
Card accuracy, precision, recall, F1, and ROC-AUC, and which to trust when classes are imbalanced or errors are asymmetric.
Neural networks and backpropagation
Make cards for activation functions, why nonlinearity matters, and how backpropagation propagates the gradient of the loss through layers.
Study tips
- Tip 1
Chunk by topic
Split Machine Learning into small decks—one per lecture, chapter, or concept—so reviews stay fast and focused.
- Tip 2
Answer before you flip
Say the answer out loud or jot a keyword before revealing the card. Active recall beats passive recognition every time.
- Tip 3
Schedule reviews
Let spaced repetition surface Machine Learning cards right before you would forget them. Cramming alone rarely sticks.
- Tip 4
Use mistakes as data
Tag or star misses and revisit them first next session—your weak spots are where the most points hide.
Common mistakes to avoid
Judging models by accuracy alone
On imbalanced data a high-accuracy model can be useless; card precision, recall, and F1 and the scenario each one exposes.
Leaking test data into training
Fitting the scaler or selecting features on the full dataset inflates results; drill that all preprocessing must be fit on the training split only.
Collecting algorithm names without assumptions
Knowing that k-NN exists is not knowing when to use it; add the data assumption and failure mode to every algorithm card.
Sample Machine Learning flashcards
A few cards students actually use for Machine Learning. Save a deck in NoteFren to study them with spaced repetition.
Tap a card to check yourself.
1
How does supervised learning differ from unsupervised learning?
Show answerHide answer
Supervised learns from labeled examples; unsupervised finds structure in unlabeled data.
2
What does gradient descent do?
Show answerHide answer
Updates the parameters by stepping opposite the gradient of the loss.
3
What is the telltale sign of overfitting?
Show answerHide answer
Low training error with much higher validation error.
4
How does L1 regularization differ from L2 in its effect on weights?
Show answerHide answer
L1 drives many weights to exactly zero; L2 shrinks weights without zeroing them.
5
What is precision?
Show answerHide answer
True positives ÷ predicted positives: how many flagged items are actually positive.
6
What is recall?
Show answerHide answer
True positives ÷ actual positives: how many real positives the model found.
7
What does k-means clustering minimize?
Show answerHide answer
The sum of squared distances from each point to its cluster's centroid.
8
What is backpropagation?
Show answerHide answer
Using the chain rule to compute the loss gradient for every weight, from the output layer backward.
Frequently asked questions
Yes. NoteFren turns your notes and photos into smart flashcards with spaced repetition and active recall—ideal for mastering Machine Learning without retyping everything.
NoteFren is an iOS app built for focused study sessions. Check the App Store listing for the latest connectivity and sync details.
Absolutely. Every card can be edited, merged, or deleted so your deck matches exactly what you need to learn.
Related subjects & guides
Create your own flashcards
Upload your notes or a PDF and get a deck you can study — free, in your browser.
Works in your browser — no download needed.