AI
No description yet. This curated deck is ready for daily study.
Card preview (24)
Where was the conference held in 1956 which saw the first public mention of the term artificial intelligence?
Dartmouth
Who came up with the term artificial intelligence during his preparations for the 1956 conference in Dartmouth?
John McCarthy
What does DARPA abbreviate?
Defense Advanced Research Project
What was the programming language Prolog originally designed for?
natural language processing and AI applications, particularly computational linguistics It works by expressing problems as facts and rules in first-order logic (Horn clauses), then uses unification and backtracking to perform automated reasoning — effectively proving whether a query follows from the given knowledge base.
According to the theory of Russell–Norvig, which disciplines laid the foundations of AI?
Philosophy, mathematics, economics (decision and game theory), neuroscience, psychology, computer engineering, control theory & cybernetics, and linguistics.
Name a big challenge first forages into the realm of automatic translations faced in the 1960s.
word ambiguity
What are the 3 prerequisites for AI to be successful?
• Availability of data • Computational power • Mature algorithms
Please define AI winter.
periods when interest, research activities, and funding of AI projects significantly decrease
What broader category of AI systems do expert systems belong to?
Knowledge-based systems. Expert systems are a specialized subset that use a knowledge base of domain-specific facts and rules combined with an inference engine to emulate the decision-making of a human expert.
If a problem to be solved can be categorized as a decision problem, how might the knowledge be typically represented in an expert system?
as a decision tree
What was Dendral, one of the first expert systems put into practice, created to achieve?
identify organic molecules
What might have caused the downfall of expert systems?
• computational complexity of inference growing faster than linear per no. of rules • difficulty of proving consistency as the base grows • inability of rule-based systems to update their own rules and learn from experience
What are typical examples of possible rules used to flag potentially fraudulent transactions in credit institutions?
• deviation from normal customer behaviour • geographical anomalies • rapid succession of multiple small transactions • unusual transaction time • unusually high amount
What is the purpose of an expert system?
It encodes the knowledge and reasoning of domain experts into a rule-based system, enabling non-expert users to reach expert-level conclusions and decisions. knowledge base (facts and rules from experts) ► inference engine (applies the rules) ► user interface (faces the non-expert)
Who developed the perceptron in 1957?
Frank Rosenblatt American psychologist and computer scientist at the Cornell Aeronautical Laboratory
What is the basic operating principle of the perceptron?
Each input is multiplied by its corresponding weight, the weighted inputs and a bias term are summed, and the result is passed through a step function (activation function) that produces a binary output — 1 if the sum exceeds a threshold, 0 otherwise.
What are the typical components of a perceptron?
• input: x1, x2, x3 • weights: w1, w2, w3 • transfer function: Σ • activation function • output: y
When was the backpropagation algorithm introduced by Rumelhart et al.?
1986
What does the backpropagation algorithm allow the neural network to do?
learn from errors by gradually adjusting the connection weights to improve predictions
What does the number of neurons in the input layer correspond to in ANNs?
the no. of features in the input data
What does the number of neurons in the output layer correspond to in ANNs?
the no. of output classes or output variables
What are the main architectural characteristics of feed-forward neural networks?
• the outputs of neurons are only connected to the next layer • the information only flows in one direction
What does the term GAN abbreviate in the context of the history of generative AI?
generative adversarial networks
What does GPT abbreviate in the context of AI?
generative pre-trained transformers