Artificial Intelligence Flashcards
Turing Test
a test of a machine’s ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human.
CAPTCHA
“Completely Automated Public Turing Test to tell Computers and Humans Apart”. Used to prove to a website that a user is a human and not a bot
Weak/Narrow AI
artificial intelligence that has a limited function or can only perform a specific task
Domain-specific AI
Artificial Intelligence that performs tasks better than humans in certain domains
Strong AI
Artificial intelligence that can develop consciousness and make decisions better than humans
Super AI
Artificial intelligence that surpass human intelligence
singularity
the hypothetical future where AI becomes so advanced that it is superior to human intelligence
expert system
a computer system that acts like a human expert in a specific subject area
knowledge base
facts and rules in an expert system
inference engine
the part of an expert system that uses programmed rules to interpret and evaluate the facts in the knowledge base
training data
a collection of labeled information used to train a machine learning model
supervised learning
The algorithm learns from labeled data, where the desired output is known
unsupervised learning
The algorithm learns from unlabeled data, discovering hidden patterns and structures
reinforced learning
a type of machine learning where an “agent” learns to behave in an environment by performing actions and receiving feedback in the form of rewards or penalties
deep learning
a type of machine learning that is used for more complex problems. It does not require structured data, but instead uses artificial neural networks
deep learning: natural language processing
deals with the interaction between computers and human (natural) languages. Essentially, it’s about enabling computers to understand, interpret, and generate human language in a valuable way
deep learning: image recognition
used to understand what is in a picture so that it can describe the picture and make it more searchable
deep learning: voice and sound recognition
works by analyzing patterns of sound that can be converted into text and applied to natural language processing
deep learning: sentiment analysis
can interpret someone’s mood or intent using pattern recognition
