Exploring Artificial Intelligence Use Cases and Applications

Question 1

Artificial Intelligence

Answer 1

AI is a broad field that encompasses the development of intelligent systems capable of performing tasks that typically require human intelligence, such as perception, reasoning, learning, problem-solving, and decision-making. AI serves as an umbrella term for various techniques and approaches, including machine learning, deep learning, and generative AI.

Question 2

Machine Learning

Answer 2

ML is subset of AI for understanding and building methods that make it possible for machines to learn. These methods use data to improve computer performance on a set of tasks.

ML models learn patterns and relationships from data rather than relying on hard-coded rules for instructions. These models are trained on large datasets, and their accuracy and performance improve over time as they process more data.

Question 3

Deep Learning

Answer 3

Deep learning uses the concept of neurons and synapses similar to how our brain is wired.

Question 4

Generative AI

Answer 4

Generative AI is a subset of deep learning because it can adapt models built using deep learning, but without retraining or fine tuning.

Generative AI is capable of generating new data based on the patterns and structures learned from training data.

It can create new content, including conversations, stories, images, videos, music, and code.

Question 5

Computer vision

Answer 5

Computer vision is a field of artificial intelligence that allows computers to interpret and understand digital images and videos. Deep learning has revolutionized computer vision by providing powerful techniques for tasks such as image classification, object detection, and image segmentation.

Question 6

Natural language processing

Answer 6

NLP is a branch of artificial intelligence that deals with the interaction between computers and human languages. Deep learning has made significant strides in NLP. It can perform tasks such as text classification, sentiment analysis, machine translation, and language generation.

Question 7

Intelligent document processing (IDP)

Answer 7

IDP is an application that extracts and classifies information from unstructured data, generates summaries, and provides actionable insights.

Question 8

Fraud detection

Answer 8

Fraud detection refers to the process of identifying and preventing fraudulent activities or unauthorized behavior with a system, process, or transaction.

Question 9

When is ML NOT a good choice?

Answer 9

You do not need ML if you can determine a target value using simple rules, computations, or predetermined steps. You can program the steps without needing any data-driven learning.

Question 10

When IS ML a good choice?

Answer 10

(1) Coding the rules is challenging: Many human tasks cannot be solved properly using simple, rule-based solutions.

(2) Scale of the project is challenging: Millions of items

Question 11

Supervised learning

Answer 11

In supervised learning, the algorithms are trained on labeled data. The goal is to learn a mapping function that can predict the output for new, unseen input data.

The supervisor is labeled training data.

Question 12

Unsupervised learning

Answer 12

Unsupervised learning refers to algorithms that learn from unlabeled data. The goal is to discover inherent patterns, structures, or relationships within the input data.

Question 13

Reinforcement learning

Answer 13

In reinforcement learning, the machine is given only a performance score as guidance and semi-supervised learning, where only a portion of training data is labeled. Feedback is provided in the form of rewards or penalties for its actions and the machine learns from this feedback to improve it decision-making over time.

Question 14

Classification

Answer 14

Classification is a supervised learning technique used to assign labels or categories to new, unseen data instances based on a trained model. The model is trained on a labeled dataset, where each instance is already assigned to a known class or category. The goal of classification is to learn patterns from the training data and use them to predict the class or category for new unlabeled data instances.

Use cases include the following:
(1) Fraud detection
(2) Image classification
(3) Customer retention
(4) Diagnostics

Question 15

Regression

Answer 15

Regression is a supervised learning technique used for predicting continuous or numerical values based on one or more input variable. It is used to model the relationship between a dependent variable (the value to be predicted) and one or more independent variables (the features or inputs used for prediction).

Use cases include the following:

(1) Advertising popularity prediction
(2) Weather forecasting
(3) Market forecasting
(4) Estimating life expectancy
(5) Population growth prediction

Question 16

Clustering

Answer 16

A common subcategory of unsupervised learning is clustering. This kind of algorithm groups data into different clusters based on similar features or distances between the data point to better understand the attributes of a specific cluster.

For example, by analyzing customer purchasing habits, an unsupervised algorithm can identify a company as being large or small.

Use cases include the following:

(1) Customer segmentation
(2) Targeted marketing
(3) Recommended systems

Question 17

Dimensionality reduction

Answer 17

Dimensionality reduction is an unsupervised learning technique used to reduce the number of features or dimensions in a dataset while preserving the most important information or patterns.

Use cases include the following:

(1) Big data visualization
(2) Meaningful compression
(3) Structure discovery
(4) Feature elicitation