7 cards66 people studying this

Machine Learning Concepts

Key ML concepts — supervised vs unsupervised learning, neural networks, overfitting, and evaluation metrics.

Share on XWhatsApp
Study this deck for free

Free account includes unlimited cards, FSRS v6 scheduling, and AI card generation.
No credit card required.

Try it — tap the card
What is the difference between supervised and unsupervised learning?
92% likely forgotten
Tap to see the answer
Supervised: learns from labeled data (classification, regression). Unsupervised: finds patterns in unlabeled data (clustering, dimensionality reduction).
Tap to flip back
What is overfitting?
Last reviewed 12 days ago
Tap to see the answer
When a model learns noise in training data instead of the underlying pattern. Performs well on training data but poorly on new data. Fix: regularization, more data, simpler model.
Tap to flip back
What is gradient descent?
87% likely forgotten
Tap to see the answer
An optimization algorithm that minimizes a loss function by iteratively adjusting parameters in the direction of steepest descent. Learning rate controls step size.
Tap to flip back
What is a neural network?
Fading — due 5 days ago
Tap to see the answer
Layers of interconnected nodes (neurons). Input layer, hidden layers, output layer. Each connection has a weight. Learns by adjusting weights via backpropagation.
Tap to flip back
What is the bias-variance tradeoff?
79% likely forgotten
Tap to see the answer
High bias = underfitting (too simple). High variance = overfitting (too complex). Goal: find the sweet spot that minimizes total error.
Tap to flip back
What is precision vs recall?
Last reviewed 21 days ago
Tap to see the answer
Precision: of predicted positives, how many are correct (TP/TP+FP). Recall: of actual positives, how many were found (TP/TP+FN). F1 score balances both.
Tap to flip back
What is cross-validation?
94% likely forgotten
Tap to see the answer
A technique to evaluate model performance by splitting data into K folds. Train on K-1 folds, test on remaining. Repeat K times. Reduces evaluation variance.
Tap to flip back
Create your own AI flashcards

Create your own AI flashcards in 30 seconds — free

Get started for free

Want to track your progress with spaced repetition?

Sign up free to save this deck

Made with Forgetless — the AI flashcard app

Create your own deck in 30 seconds. Powered by the same algorithm as Anki.

Start free