Scribd
Upload
2 views9 pages

Machine Learning Key Terminologies Guide

The document outlines key terminologies in machine learning, including datasets, features, labels, models, and inference. It describes types of learning such as supervised, unsupervised, and reinforcement learning, along with concepts of training, testing, and validation. Additionally, it covers performance metrics, algorithms, and common terminologies like hyperparameters and learning rates.

Uploaded by

Anam Qureshi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views9 pages

Machine Learning Key Terminologies Guide

The document outlines key terminologies in machine learning, including datasets, features, labels, models, and inference. It describes types of learning such as supervised, unsupervised, and reinforcement learning, along with concepts of training, testing, and validation. Additionally, it covers performance metrics, algorithms, and common terminologies like hyperparameters and learning rates.

Uploaded by

Anam Qureshi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Machine Learning

Terminologies
Week 02
Instructor: Dr. Anam Qureshi
Key Terminologies
● Dataset: A collection of data used for training and testing a model.
● Feature: An individual measurable property or characteristic of data.
● Label: The output or target value in supervised learning.
● Model: The mathematical representation of a problem.
● Inference: The process of making predictions using a trained model. Happens
after deployment.
● Hypothesis: A formal representation or function proposed by the learning
algorithm to approximate the true relationship between input features and output
labels
Types of Learning
● Supervised Learning:
○ Input data is labeled.
○ Example: Predicting house prices.
● Unsupervised Learning:
○ Input data is not labeled.
○ Example: Customer segmentation.
● Reinforcement Learning:
○ Learning by interacting with an environment.
○ Example: Game playing bots.
Training, Testing, and Validation
● Training Set:
○ The subset of data used to train the model.
● Validation Set:
○ Used to tune model parameters.
● Test Set:
○ Evaluates the final performance of the model.

Testing vs. Inference:

● Testing: Measures model performance on a test dataset during development.


● Inference: Applies the trained model to real-world, unseen data after deployment.
Overfitting and Underfitting
● Overfitting:
○ Model performs well on training data
but poorly on unseen data.
○ Example: Memorizing data.
● Underfitting:
○ Model is too simple to capture the
underlying patterns.
○ Example: High bias.
Key Performance Metrics
● Accuracy: Percentage of correct
predictions.
● Precision: True positives / (True positives
+ False positives).
● Recall: True positives / (True positives +
False negatives).
● F1 Score: Harmonic mean of precision and
recall.
● Loss or Error Function: A mathematical
function that quantifies the difference
between predicted and actual values.
Common examples include Mean Squared
Error (MSE) and Cross-Entropy Loss.
Algorithms Overview
● Regression: Predicts continuous values.
● Classification: Predicts discrete categories.
● Clustering: Groups similar data points.
● Dimensionality Reduction: Reduces the number of features.
Some common terminologies

● Hyperparameters: Parameters set before training.


● Weights: Values adjusted during training.
● Learning Rate: Controls how much weights are updated.
● Epoch: One complete pass through the training dataset.

You might also like