Exploring Artificial Intelligence Use Cases and Applications Flashcards

1
Q

What is AI?

A

Artificial Intelligence I 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.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is ML?

A

Machine Learning 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.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is DL?

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is Generative AI?

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Computer vision

A

Computer vision is a field of artificial intelligence that allows computers to interpret and understand digital images and videos.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Intelligent document processing

A

IDP is an application that extracts and classifies information from unstructured data, generates summaries, and provides actionable insights. (use cases included identifying incomplete load info in underwriting, processing court docs & claims and doctors notes)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Supervised learning

A

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.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Unsupervised Learning

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Reinforcement learning

A

Machine Learning Technique: 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.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Regression learning

A

Machine Learning Technique - supervised learning technique used for predicting numerical values based on one input variables. Use cases include weather forecasting, marketing forecasting, etc.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Classification Learning

A

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. (use cases include fraud deduction, image classification, customer retention, etc.)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Clustering

A

(unsupervised learning) 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. Use cases: customer segmentation, targeted marketing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Dimensionality reduction

A

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: big data visualization,

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Reinforcement learning

A

Unlike supervised and unsupervised learning, reinforcement learning improves its model by mining feedback from previous iterations. In reinforcement learning, an agent continuously learns through trial and error as it interacts in an environment.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Nondeterminism

A

challenge where the model produces different outputs each time it runs with the same input data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Toxicity

A

occurs when the model is generating content that is inflammatory, offensive, or inappropriate.