Please enable JavaScript.
Coggle requires JavaScript to display documents.
AI and ML - Coggle Diagram
AI and ML
Practical applications of AI
Modern web search engines
Personal assistant programs that understand spoken language
Self-driving vehicles
Recommendations engines (like those used in Spotify and Netflix)
Practical applications of ML
Fraud detection
Self Driving vehicles
Product recommendations
Social media
What is artificial intelligence?
Refers to processes and algorithms that are able to simulate human intelligence, including mimicking cognitive functions such as perception, learning and problem solving.
Deep learning (DL) and Machine Learning (ML) are subsets of AI
Types of AI
Reactive machines
Reactive machines are able to perform basic operations based on some form of input.
Limited memory AI
These systems are able to store incoming data and data about any actions or decisions it makes, and then analyze that stored data in order to improve over time.
Theory of mind
This is at theoretical level and has not been achieved yet
AIs would begin to understand human thoughts and emotions, and start to interact with us in a meaningful way.
The relationship between human and AI becomes reciprocal, rather than the simple one-way relationship humans have with various less advanced AIs now.
Self awareness
This is considered as the ultimate goal of AI, where AI has the consciousness of humans and are aware of themselves as beings in the world with similar desires and emotions as humans.
What is machine learning?
Machine learning (ML) is a subset of AI that falls within the “limited memory” category in which the AI (machine) is able to learn and develop over time.
Types of ML
Supervised learning
AI is actively given feedback by humans to fix the algorithm created.
A good example of supervised learning is email filtering. There are mails that are categorized as spam. However, if the user says that the mail is not spam, then the AI understand what types of mails are spam and what are not.
Unsupervised learning
This involves no help from humans. AI creates its own algorithms based on the data given to it and alters it if there is a change.
Reinforcement learning
AI learns by interacting with the environment in which it is placed. It receives positive or negative rewards based on the actions it takes, and improves over time by refining its responses to maximize positive rewards.