AI Flashcards

1
Q

What is Artificial intelligence

A

The simulation of intelligent behaviour by a computerwhich enables it to make decisions without humanintervention

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

What are the 3 enablers of AI

A

The exponential growth in the speed of computersHuang’s LawCloud computing

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

Describe Narrow AI

A

AI focuses on a specific, singular or limited taskExamples include image recognition, hyperpersonalisation, chatbots, predictive text.Trained on specific tasks by data scientistsCorrelates questions or assignments to a specific dataset to accomplish a task.No self-awareness, consciousness, ability to think

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

Describe General AI

A
  • Seeks machines that can handle a range of cognitivetasks with little oversight.* The ability to learn, generalise, apply knowledge and planfor the future.* Must consistently pass the Turing test.* Single, general intelligence that possesses commonsense and creativity and expresses emotions.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is Machine Learning

A

Machine learning (ML) is a subset of Artificial Intelligence (AI) in terms of algorithms that can adapt without following explicit instructions.

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

What can Machine learning do?

A

can train a machine how to learnAutomates analytical model buildingIs a branch of artificial intelligence based on theidea that systems can learn from data, identifypatterns, and make decisions with minimal humanintervention

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

What is Supervised learning

A

You provide a data set that has pictures of apples. Then another data set that lets the model know that those are pictures of apples. Finally, a new set of data that only contains pictures of apples. At this point the system can recognise what the fruit isand will remember it.

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

What is Unsupervised learning

A

You provide a collection of pictures of different kinds of fruit. The model analyses this to try and recognise any patterns. The machine categorises the picture into different types based on their similarities, and one of these categories would be mostly apples.

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

What is semi-supervised learning

A

You provide the machine with a data set of images and ask it to identify a fruit. The machine picks an image of an apple and tells you it is an orange. You feedback to the system that it is actually an apple. The machine remembers this and picks again.You provide feedback once more. This continues whilst the machine learns from itsexperiences and feedback.

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

What are the different types of AGI testing

A

The Turing testWozniak/Goertzel’s Coffee TestNilsson’s Employment TestGoertzel’s Robot College Student Test

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

What is Wozniak/Goertzel’s Coffee test

A

As a part of the coffee test, the AI application has to go to a house and make coffee. The programme has to go to any kitchen and find the ingredients required and then perform the task of making a coffee.

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

What is the Turing test

A

A remote human interrogator, within a fixed time frame, must distinguishbetween a computer and a human subject based on their replies to various questions posed by the interrogator

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

What is Nilsson’s employment

A

To pass this test, the AI program should be able to perform jobs that are performed by humans

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

What is Goertzel’s Robot College Student test

A

This test advocates an AI being enrolled in a college and getting a degree using the same resources as other students enrolled for the same degree.

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

What is meant by conditional probability

A

In probability theory, conditional probability is a measure of the probability of an event given that (by assumption, presumption, assertion, or evidence) another event has occurred.

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

What is meant by suggestion engines

A

A suggestion or recommendation engine is a system that suggests products, services, and information to users based on an analysis of data

17
Q

What is meant by pattern recognition

A

Pattern recognition is the use of machine learning algorithms to identify patterns. It has been applied in various fields such as image analysis, computer vision, healthcare,

18
Q

What are the 4 neural networks

A

Massive modelsMassive DataTrial & ErrorDeep learning

19
Q

What is meant by massive models

A

DeepMind has created a deep neural network with more than 100 billion parameters. These are the values in the network that get tweaked over and over again during training. The size of a model is measured by the number of parameters it has - the more parameters, the more data it can soak up.

20
Q

What is meant by massive data

A

Neural networks can be thought of as a “brute force” technique, characterised by a lack of intelligence but a huge amount of data, because they start with a blank slate, and they hammer their way through to an accurate model

21
Q

What is meant by trial and error

A

Training a neural network is a highly iterative process, or a trial and error process. The process is to turn an idea into code, experiment, and evaluate the outcome and make changes and repeat the process until you get the expected or otherwise satisfactory outcome.

22
Q

What is meant by deep learning

A

Deep learning is a type of machine learning that uses multiple layers to progressively extract higher-level features from the raw input.

23
Q

What are common uses of AI

A

translation engines* healthcare* cyber security* transport* entertainment* education (to detect plagiarism)* voice command (voice to text/smart data)* social networking (auto tagging)* shopping (search/recommendation)* finance (fraud/credit)* communication (filtering)

24
Q

What is meant by SLAM

A

is the computational problem of constructing or updating a map of an unknown environment while simultaneously keeping track of an object’s location within it

25
Q

What is meant by language recognition

A

Natural language processing is a subfield of computer scienceconcerned with the interactions between computers and human language.

26
Q

What is meant by machine translation

A

Machine translation is the process of automatically translating content fromone language (the source) to another (the target) without any human input.

27
Q

What is meant by anomaly detection

A

Anomaly detection (aka outlier analysis) is a step in data mining thatidentifies data points, events, and/or observations that deviate from a dataset’s normal behaviour.

28
Q

What is meant by image recognition

A

Image recognition is the ability of software to identify objects, places, people,writing and actions in images.

29
Q

What are the types of problems AI can solve

A
  • Simultaneous Location and Mapping (SLAM)* language recognition* machine translation* anomaly detection* image recognition