Unit 6.3 - artificial intelligence

Question 1

What is artificial intelligence?

Answer 1

A branch of computer science dealing the the simulation of intelligent human behaviors by computers; it refers to a system’s ability to correctly interpret external data, to learn from it and to use those relevant learning to achieve specific tasks through flexible adaptation. Its data model of past experiences help it plan & predict.

Question 2

4 main characteristics of AI

Answer 2

1. Collection of data
2. Rules for using/analyzing the data
3. Ability to reason & detect patterns
4. Update understanding & make decisions

Question 3

Fundemental principle of how AI works

Answer 3

Training AI machine to recognize and remember patterns by feeding it with lots of examples, then feeding the machine new data and letting it decide what to do with it/reason independent of human interference.

Question 4

What is Big Data?

Answer 4

Huge amounts of data that allow deep analysis of patterns and predictions of behaviors by AI.

Question 5

What is an expert system?

Answer 5

Systems that rely on humans to constantly update their data model and rules required to process the data in order to provide information to human experts by data analysis (which they perform by applying rules to the massive amounts of stored data in order to infer results)
They imitate the decision-making ability of human experts and are designed to solve complex problems based on set of information and rules.

Question 6

Declarative programming

Answer 6

A type of programming where the intended outcome, along with the data model and rules are created but the precise steps to achieve the outcome are generated by the computer.

Question 7

4 things required by expert system

Answer 7

1. Knowledge base - contains facts and data
2. Rules base - contains rules & logic (IF THEN conditions) which expert systems use to arrive at a conclusion
3. Inference engine - machine that processes rules & logic in order to arrive to a conclusion/result
4. Interface to allow the user to enter querries and view results

Question 8

Machine learning

Answer 8

The application of computer algorithm that improves automatically through experience. It’s trained to discover patterns in data and make predictions & decisions based on those past patterns; capable of updating their own data models when they encounter new data. It uses statistical techniques to learn how to get progressively better at a task, without having been specifically coded for the purpose.

Question 9

Deep learning

Answer 9

Type of machine learning that runs inputs through a biologically inspired neural network architecture which contains a number of hidden layers through which the data is processed, allowing the machine to go deep in its learning, making connections and weighing input for the best results.

Question 10

4 real-world applications of AI

Answer 10

1. Self-driving cars
2. Smart assistants
3. Interpreting medical images
4. Fraud detection

Question 11

3 types of artificial intelligence

Answer 11

1. ANI - artificial narrow intelligence which specializes one area and solves one particular problem; machine learning
2. AGI - artificial general intelligence which refers to a computer that is as smart as a human across the board; machine intelligence
3. ASI - artificial super intelligence which is an intellect that is much smarter than the best human brains in almost every field; machine consciousness

Question 12

What type of data does machine learning use to predict future outcomes?

Answer 12

Historical data

Question 13

What type of data does machine learning work with?

Answer 13

All types of data - images, sounds, text, numbers, temperature readings and more!

Question 14

Advantages vs disadvantages of expert systems

Answer 14

+ high level of accuracy & expertise, consistent results, faster response than human experts, can store large amounts of data & facts
- only as good as the data entered into the system, optimal use requires training, responses can be cold & lack humanity, may still make mistakes

Question 15

3 examples of expert systems

Answer 15

Diagnosing medical problems;
financial calculations;
diagnosing faults in equipment;

Question 16

3 examples of machine learning

Answer 16

1. Online customer support chat-bots
2. Self-driving cars
3. Tailored ads

Question 17

3 key differences between expert systems and machine learning

Answer 17

1. Expert systems have no learning capabilities and must be manually programmed while machine learning learns automatically from data inputs
2. ES mimics expert decision-making by using a set of rules while ML discovers patterns in data in order to make predictions
3. ES require humans to update their data models while ML can update them themselves when learning from new data

Question 18

Advantages of machine learning (e.g. in robotics)

Answer 18

1. Can help robot be more flexible/adapt to new situations by updating its rule base
2. Make it more efficient by having greater knowledge of (for example) surroundings