1: Giving Computers the Ability to Learn From Data

Question 1

Three types of machine learning

Answer 1

Unsupervised, Supervised, Reinforcement Learning

Question 2

What’s the main goal in supervised learning?

Answer 2

To learn a model from labeled training data that allows us to make predictions about unseen or future data.

Question 3

What are the two main subcategories of supervised learning?

Answer 3

Classification - output is label and regression - output is continuous value

Question 4

What is the goal of classification?

Answer 4

To predict the categorical class labels of new instances based on past observations. Those class labels are discrete, unordered values that be understood as the group memberships of the instances.

Question 5

Describe regression analysis.

Answer 5

We are given a number of predictor (explanatory) variables and a continuous response variable (outcome), and we try to find a relationship between those variables that allows us to predict an outcome.

Question 6

What’s the goal of reinforcement learning?

Answer 6

To develop a system (agent) that improves its performance based on interactions with the environment. The current state of the environment typically also includes a so-called reward signal (related to supervised learning). However, the feedback is not the correct ground truth label or value, but a measure of how well the action was measured by a reward function. Through the interaction, an agent can then use reinforcement learning to learn a series of actions that maximizes this reward via an exploratory trial-and-error approach or deliberative planning.

Question 7

Describe reinforcement learning diagram:

Answer 7

Agent – state –> Environment – Action –> && – Reward –> Agent

Question 8

What are two examples of unsupervised learning?

Answer 8

Clustering and Dimensionality Reduction for data compression.

Question 9

Describe the four stages in a typical workflow diagram for using machine learning in predictive modeling

Answer 9

1) Preprocessing (Feature Extraction and Scaling, Feature Selection, Dimentionality Reduction, Sampling)
2) Learning (Model Selection, Cross-Validation, Performance Metrics, Hyperparameter Optimization)
3) Evaluation
4) Prediction