LESSON 1: Introduction to Machine Learning

Machine learning

______ is about extracting knowledge from data.

Machine learning

It is a research field at the intersection of statistics, AI, and computer science and is also known as predictive analytics or statistical learning

predictive analytics

It is a research field at the intersection of statistics, AI, and computer science and is also known as ______ or statiscal learning

statiscal learning

It is a research field at the intersection of statistics, AI, and computer science and is also known as predictive or ______________

Spam filter

is the first ML application developed in 1990s

supervised learning

unsupervised learning

self-supervised learning

semi-supervised learning

reinforcement learning

Types of Machine Learning

Machine Learning

can be classified according to the amount and type of supervision they get during training.

Supervised Learning

is a ML algorithms that learn from input/output pairs.

Supervised Learning

In _________, the training set you feed to the algorithm includes the desired solutions, called labels.

labels

In Supervised Learning, the training set you feed to the algorithm includes the desired solutions, called _____

Supervised learning

is commonly used in applications where historical data predicts likely future events.

Classification

Regression

There are certain tasks that fall under supervised learning:

target

The word target and label are generally treated as synonyms in supervised learning, but ______ is more common in regression tasks and label is more common in classification tasks.

regression task

The word target and label are generally treated as synonyms in supervised learning, but target is more common in _______ and label is more common in classification tasks.

label

The word target and label are generally treated as synonyms in supervised learning, but target is more common in regression and _____ is more common in classification tasks.

classification task

The word target and label are generally treated as synonyms in supervised learning, but target is more common in regression and label is more common in

features

Moreover ______ are sometimes called predictors or attributes. These terms may refer to individual samples (e.g., ”this car’s mileage feature is equal to 15000”).

predictors or attributes

Moreover features are sometimes called_______. These terms may refer to individual samples (e.g., ”this car’s mileage feature is equal to 15000”).

classification

A typical supervise learning task is

machine learning program

Your spam filter is a _________, that given an examples of spam emails and ham emails, can learn to flag spam.

training set

The examples that the system uses to learn are called the ____

training instance

Each training example is called a ______ (or sample).

model

The parts of a ML that learns and makes prediction is called a ____(e.g. neural net)

accuracy

The particular performance measure that correctly classified emails is called ____.

regression

Another typical task is to predict a target numeric value, such as the price of a car, given sets of features (mileage, age, brand, etc.) This sort of task is called ______.

logistic regression

______ is commonly used for classification, as it can output a value that corresponds to the probability of belonging to a given class (e.g., 20% chance of being spam).

unsupervised learning

In ______, only the input data is known, and no known output data is given to the algorithm.

unsupervised learning

In ______ the training data is unlabeled. The system tries to learn without a teacher.

• clustering

• visualization

• anomaly detection

• dimensionality reduction

• association rule learning

There are certain tasks that fall under unsupervised learning:

Clustering

______ - Grouping together unlabeled data points into categories/clusters- Data points are assigned to a cluster based on similarity. - For example, you want to detect groups of similar visitors in your blog.

Visualization

______ - In visualization, you feed them a lot of complex and unlabeled data, and they output a 2D or 3D representation of your data that can be easily plotted

Anomaly Detection

________ - Attempts to detect outliers in a dataset- For example, fraudulent transactions on a credit card.- For example, identifying the anomalies between a thousand pictures of dog and only 1% pictures of cat.

Dimensionality Reduction

_____- in which the goal is to simplify the data without losing too much information. - One way to do this is to merge several correlated features into one.

Dimensionality Reduction

For example, a car’s mileage may be strongly correlated with its age, so the dimensionality reduction algorithm will merge them into one feature that represents the car’s wear and tear. This is called feature extraction.

feature extraction

For example, a car’s mileage may be strongly correlated with its age, so the dimensionality reduction algorithm will merge them into one feature that represents the car’s wear and tear. This is called_______

Association Rule Learning

_________- in which the goal is to dig into large amounts of data and discover interesting relations between attributes. - For example, suppose you own a supermarket, and running an association rule learning on your sales logs may reveal that people who purchase barbecue sauce and potato chips also tend to buy steaks.