Lecture 1 ML

What is Training in machine learning?

The process of making the model understand desired solutions by feeding it data and adjusting its parameters

What is a Sample in machine learning?

A single representation of the input and potentially output for your dataset

What is Generalization in machine learning?

The model's ability to minimize error for unseen data

What is Supervised Learning?

A type of learning where the model is trained using labeled data

What is Unsupervised Learning?

A type of learning where the model is trained using unlabeled

What is Semi-Supervised Learning?

Learning that uses a combination of labeled and unlabeled data, typically when a company has a large amount of unlabeled data and invests in labeling only a smaller portion

What is Reinforcement Learning?

Learning where the system learns through trial and error

What are the two main subcategories of Supervised Learning?

Classification and Regression

What is Classification in machine learning?

A method of predicting the category or class given a input class and categories

What is Binary Classification?

Classification with only two possible labels (e.g., spam/not spam)

What is Multi-Class Classification?

Classification with multiple possible labels (e.g., different types of flowers)

Name 3 algorithms used for Classification

KNN, decision trees, random forests, support vector machines, Naive Bayes

What is Regression in machine learning?

A supervised learning task where the model generates a numerical output in a continuous numerical space

What is the basic formula for Linear Regression?

f(x) = wx + b (where w is weight/slope and b is bias/intercept)

Name 3 algorithms used for Regression

Linear regression, polynomial regression, decision tree regression

What is Clustering in machine learning?

An unsupervised learning technique that identifies natural groupings within data

What is Anomaly Detection in machine learning?

An unsupervised learning technique for identifying unusual patterns in data

What is Dimensionality Reduction in machine learning?

echniques to reduce the number of variables in the data

Name 3 algorithms used for Clustering

K-means, DBSCAN, hierarchical clustering

What is Transductive Learning?

Generate label predictions for the unlabeled data using existing labels

What is Inductive Learning?

Train a model on labeled data, feed unlabeled data through the model, and incorporate high-confidence predictions

What is S3VM?

Semi-Supervised Support Vector Machine, a variation of SVM for semi-supervised learning

What is an Agent in reinforcement learning?

Computer program that can observe its environment

What is a State in reinforcement learning?

Observations of the environment

What is an Action in reinforcement learning?

What the agent decides to do

What is a Reward in reinforcement learning?

Feedback on the success of an action (positive or negative)

What is Function Q in reinforcement learning?

The link between state and action leading to reward

What are Deep Q-Networks?

Reinforcement learning approach that uses deep neural networks to learn the Q function

What is Feature Engineering?

The process of selecting the most useful features

What is Feature Extraction?

The process of synthesizing appropriate features by combining existing features

What is Overfitting?

When the model performs very well on training data but poorly on unseen data