Difference between revisions of "Collective Animal Intelligence"
m |
m |
||
| Line 22: | Line 22: | ||
* [[Sakana]] ... inspired by the way that fish and other animals work together in groups | * [[Sakana]] ... inspired by the way that fish and other animals work together in groups | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| + | One of the most well-known examples of [[Bio-inspired Computing]] is Collective Animal Intelligence (CAI). CAI is the study of how groups of animals work together to achieve a common goal. Some examples of CAI include: | ||
| − | |||
| − | |||
* Schools of fish swimming together | * Schools of fish swimming together | ||
| − | * | + | * Bees |
* Termite mounds | * Termite mounds | ||
| + | * [https://en.wikipedia.org/wiki/Flocking_(behavior) Flocking (birds) | Wikipedia] | ||
| + | * [https://en.wikipedia.org/wiki/Ant_colony_optimization_algorithms Ant Colony Optimization Algorithms (insects) | Wikipedia] | ||
| + | * [https://en.wikipedia.org/wiki/Swarm_intelligence Swarm intelligence (insects) | Wikipedia] | ||
| + | * [https://en.wikipedia.org/wiki/Particle_swarm_optimization Particle Swarm Optimization | Wikipedia] | ||
| + | * [https://en.wikipedia.org/wiki/Shoaling_and_schooling Shoaling & Schooling (fish) | Wikipedia] | ||
| + | * [https://en.wikipedia.org/wiki/Herd_behavior Herd Behavior (land animals) | Wikipedia] | ||
| + | |||
These groups of animals are able to achieve complex tasks by working together in a coordinated way. They do this without any central planning or communication. Instead, they rely on simple rules of behavior that emerge from the interactions of the individual animals. Bio-inspired AI researchers are interested in understanding how these simple rules can lead to complex and intelligent behavior. They believe that by studying CAI, they can develop new AI algorithms that are more efficient, robust, and adaptive than traditional AI algorithms. | These groups of animals are able to achieve complex tasks by working together in a coordinated way. They do this without any central planning or communication. Instead, they rely on simple rules of behavior that emerge from the interactions of the individual animals. Bio-inspired AI researchers are interested in understanding how these simple rules can lead to complex and intelligent behavior. They believe that by studying CAI, they can develop new AI algorithms that are more efficient, robust, and adaptive than traditional AI algorithms. | ||
Revision as of 19:36, 19 August 2023
Youtube search... ...Google search
- Collective Animal Intelligence ... Animal Ecology ... Animal Language ... Bird Identification
- Symbiotic Intelligence ... Bio-inspired Computing ... Neuroscience ... Connecting Brains ... Nanobots ... Molecular ... Neuromorphic ... Evolutionary/Genetic
- Cybersecurity ... OSINT ... Frameworks ... References ... Offense ... NIST ... DHS ... Screening ... Law Enforcement ... Government ... Defense ... Lifecycle Integration ... Products ... Evaluating
- Sakana ... inspired by the way that fish and other animals work together in groups
One of the most well-known examples of Bio-inspired Computing is Collective Animal Intelligence (CAI). CAI is the study of how groups of animals work together to achieve a common goal. Some examples of CAI include:
- Schools of fish swimming together
- Bees
- Termite mounds
- Flocking (birds) | Wikipedia
- Ant Colony Optimization Algorithms (insects) | Wikipedia
- Swarm intelligence (insects) | Wikipedia
- Particle Swarm Optimization | Wikipedia
- Shoaling & Schooling (fish) | Wikipedia
- Herd Behavior (land animals) | Wikipedia
These groups of animals are able to achieve complex tasks by working together in a coordinated way. They do this without any central planning or communication. Instead, they rely on simple rules of behavior that emerge from the interactions of the individual animals. Bio-inspired AI researchers are interested in understanding how these simple rules can lead to complex and intelligent behavior. They believe that by studying CAI, they can develop new AI algorithms that are more efficient, robust, and adaptive than traditional AI algorithms.
