Back to AI Flashcard MakerInformation Technology /Artificial Intelligence Fundamentals Part 3
Artificial Intelligence Fundamentals Part 3
This deck covers key concepts and terminologies related to expert systems, statistical models, and reasoning methods in artificial intelligence.
Expert Systems
A computer system that emulates the decision-making ability of a human expert and are designed to solve complex problems by reasoning about knowledge, like specialist, and not by following the procedure of a developer as is the case in conventional programming.
Tap or swipe ↕ to flip
Swipe ←→Navigate
1/32
Key Terms
Term
Definition
Expert Systems
A computer system that emulates the decision-making ability of a human expert and are designed to solve complex problems by reasoning about knowledge,...
Certainty Factors
MYCIN incorporated a calculus of uncertainty called __________, which seemed (at the time) to fit well with how doctors assessed the impact of evidenc...
Frames
This concept, proposed by Marvin Minsky, "is an artificial intelligence data structure used to divide knowledge into substructures by representing "st...
Back-Propagation
A common method of training artificial neural networks so as to minimize the objective function.
Connectionist
A set of approaches in the fields of artificial intelligence, cognitive psychology, cognitive science, neuroscience and philosophy of mind, that model...
Hidden Markov Models
A statistical Markov model in which the system being modeled is assumed to be a Markov process with unobserved states. Can be considered as the simple...
Related Flashcard Decks
Study Tips
- Press F to enter focus mode for distraction-free studying
- Review cards regularly to improve retention
- Try to recall the answer before flipping the card
- Share this deck with friends to study together
| Term | Definition |
|---|---|
Expert Systems | A computer system that emulates the decision-making ability of a human expert and are designed to solve complex problems by reasoning about knowledge, like specialist, and not by following the procedure of a developer as is the case in conventional programming. |
Certainty Factors | MYCIN incorporated a calculus of uncertainty called __________, which seemed (at the time) to fit well with how doctors assessed the impact of evidence on the diagnosis. |
Frames | This concept, proposed by Marvin Minsky, "is an artificial intelligence data structure used to divide knowledge into substructures by representing "stereotyped situations." They are connected together to form a complete idea. |
Back-Propagation | A common method of training artificial neural networks so as to minimize the objective function. |
Connectionist | A set of approaches in the fields of artificial intelligence, cognitive psychology, cognitive science, neuroscience and philosophy of mind, that models mental or behavioral phenomena as the emergent processes of interconnected networks of simple units. |
Hidden Markov Models | A statistical Markov model in which the system being modeled is assumed to be a Markov process with unobserved states. Can be considered as the simplest dynamic Bayesian network. |
Data Mining | A process that results in the discovery of new patterns in large data sets. Utilizes methods at the intersection of artificial intelligence, machine learning, statistics, and database systems. |
Bayesian Network | A probabilistic graphical model (a type of statistical model) that represents a set of random variables and their conditional dependencies via a directed acyclic graph (DAG). |
Human-Level AI | That which strives for "machines that think, that learn and that create." First at Minsky's symposium in 2004. |
HLAI | Human-Level Artificial Intelligence |
Artificial General Intelligence | The search for a universal algorithm for learning and acting in any environment. Also known as Strong AI. |
Friendly AI | An artificial intelligence (AI) that has a positive rather than negative effect on humanity. |
Epistemology | The branch of philosophy concerned with the nature and scope (limitations) of knowledge. |
Bayesian Inference | A method in statistics of inference used to update the probability estimate for a hypothesis as additional evidence is learned. |
Optimization | The selection of a best element from some set of available alternatives. |
Hebbian Theory | A scientific theory in biological neuroscience which explains the adaptation of neurons in the brain during the learning process. |
Neuroevolution | A form of machine learning that uses evolutionary algorithms to train artificial neural networks. It is useful for applications such as games and robot motor control, where it is easy to measure a network's performance at a task but difficult or impossible to create a syllabus of correct input-output pairs for use with a supervised learning algorithm. |
Evolutionary Algorithm | A subset of evolutionary computation, a generic population-based metaheuristic optimization algorithm. An EA uses some mechanisms inspired by biological evolution: reproduction, mutation, recombination, and selection. |
Evolutionary Computation | A subfield of artificial intelligence (more particularly computational intelligence) that involves combinatorial optimization problems. |
Markov Model | A stochastic model that assumes the Markov property. This assumption enables reasoning and computation with the model that would otherwise be intractable. |
Markov Property | Refers to the memoryless property of a stochastic process. |
Stochastic Calculus | A branch of mathematics that operates on stochastic processes. It allows a consistent theory of integration to be defined for integrals of stochastic processes with respect to stochastic processes. It is used to model systems that behave randomly. |
Graphical Model | A probabilistic model which represents the conditional independence structure between random variables. They are commonly used in probability theory, statistics—particularly Bayesian statistics—and machine learning. |
Strong AI | Artificial intelligence that matches or exceeds human intelligence — the intelligence of a machine that can successfully perform any intellectual task that a human being can. Also referred to as "artificial general intelligence" or as the ability to perform "general intelligent action." |
Nouvelle (Nouvelle AI) | During the late 1980s, this AI approach which was pioneered at the MIT Artificial Intelligence Laboratory by Rodney Brooks. It is different from classical artificial intelligence in that it tries not to reach for human-level performance, but rather tries to create systems with intelligence at the level of insects. This approach had a large impact in Europe. |
Situated Approach | A "bottom-up" approach towards agent design with a narrow focus on behaving usefully in an environment and on the the basic perceptual and motor skills required to survive. Gives a much lower priority to abstract reasoning or problem-solving skills of other agent design approaches. |
Embodied Cognition | Directly simulating the functions we associate with the body (such as perception and motion) without using logic or any similar representation. |
AI winter | A period of reduced funding and interest in artificial intelligence research. The field has experienced several cycles of hype, followed by disappointment and criticism, followed by funding cuts, followed by renewed interest years or decades later. There were two major instances in 1974-80 and 1987-93. |
Inference | The act or process of deriving logical conclusions from premises known or assumed to be true. The conclusion drawn is also called an idiomatic. |
Deductive Reasoning | The process of reasoning from one or more general statements regarding what is known to reach a logically certain conclusion. Involves using given true premises to reach a conclusion that is also true. |
Inductive Reasoning | A kind of reasoning that constructs or evaluates propositions that are abstractions of observations of individual instances of members of the same class. Contrasts with reasoning where a general conclusion is arrived at by specific examples. |
Analogy | A cognitive process of transferring information or meaning from a particular subject (the source) to another particular subject (the target). |