Artificial Intelligence Flashcards
What is AI?
It is a simulation of computer intelligent behavior, focusing on the abilities of machines to make selections and decision based on different factors
What are the types of intelligences?
1) narrow AI
2) General AI
3) Super AI
What is the history of AI?
1950: the turning test imitation game by Alan Turing
1955 John McCarthy first lined the term AI
11956-1974 the golden years (game playing, machine translation)
1974-1979 AI Winter (financial setbacks, funding of AI disappeared, limited computer power)
1980: AI boom (expert system to solve domain-specific problems)
1997: Deep Blue (IBM) beats Garry Kasparov (WORLD CHESS CHAMPION)
2012: deep learning revolution
What is data science & data analytics?
Uses scientific algorithms and tools to extract knowledge and insights from structured and unstructured data (knowledge representation, automated reasoning) it can take decisions by accurate & efficient analysis of large amount of data, replacing consultant’s used to make decisions, it also helps business companies predict future trends and outcomes
What is machine & deep learning?
Machine learning is: algorithms with the ability to learn without being explicitly programmed
Deep learning: subset of machine learning in which artificial neural networks adapt and learn from vast amount of data
What are the field of AI?
1) medicine
2) AI applications
3) Autonomus cars
4) Gaming
5) Smart homes
6) Cleaning oceans
What is meant by narrow AI?
- The only form of AI humanity have achieved until now
- Good at performing a single task within a limited context/field
- like: playing chess, making purchase suggestions, googles translate engine
What is General AI?
Human-level AI/strong AI includes understanding and reasoning its environment as a human world (how do we perceive things, juggle between multiple unrelated thoughts, making use of memories when making a decision)
What is Super AI?
It is when AI becomes much smarter than human brains in every field.
What is the turning test?
What is the subfields of AI?
1) neural networks
2) planning
3) robotics
4) matinee learning
5) natural language processing
6) perception
7) knowledge
8) cognitive system
What is visual AI?
1) pattern recognition (predicts patterns with high amount of accuracy)
2) computer vision (interprets info from images/videos)
Examples:
- facial AI
- Natural language processing (Siri, Alexa, etc)
- Text recognition (detects fake news)
- fraud detection (used by banks to detect fake bills)
- fingerprint detection
Machine learning vs deep learning
Machine learning:
- subset of AI
- train on smaller data sets
- requires more human intervention to correct and learn
- shorter training and lower accuracy
- a study of algorithms and models to perform a task without explicit instructions (erects spam emails)
Deep learning:
- subset of machine learning
- requires large amount of data
- learn from its own from the environment and past mistakes
- longer training and higher accuracy
- learn from large amount of data using neural networks like tossing bot (princeton)