Difference between revisions of "Bio-inspired Computing"
m (→Swarm) |
m |
||
| Line 29: | Line 29: | ||
[https://en.wikipedia.org/wiki/Bio-inspired_computing Bio-inspired Computing] is a subset of [https://en.wikipedia.org/wiki/List_of_metaphor-based_metaheuristics metaphor-based metaheuristics] | [https://en.wikipedia.org/wiki/Bio-inspired_computing Bio-inspired Computing] is a subset of [https://en.wikipedia.org/wiki/List_of_metaphor-based_metaheuristics metaphor-based metaheuristics] | ||
| − | The world of AI has a lot of things around it to thank for its existence in our technological landscape of today. Not only have humans spent decades of research perfecting the mathematical calculations to make these wonderfully complex learning algorithms work but during this time we have looked further than our own species as inspiration to make the next generation of intelligent presence on our planet. Mother Nature, and all that it encompasses, has it’s roots firmly planted in the workings of Artificial Intelligence — and it’s here to stay. [https://towardsdatascience.com/5-ways-mother-nature-inspires-artificial-intelligence-2c6700bb56b6 5 Ways mother nature inspires artificial intelligence | Luke James - Towards Data Science] | + | Bio-inspired AI or Nature-inspired AI is a branch of artificial intelligence that seeks to develop intelligent agents by mimicking the behavior of natural systems. The world of AI has a lot of things around it to thank for its existence in our technological landscape of today. Not only have humans spent decades of research perfecting the mathematical calculations to make these wonderfully complex learning algorithms work but during this time we have looked further than our own species as inspiration to make the next generation of intelligent presence on our planet. Mother Nature, and all that it encompasses, has it’s roots firmly planted in the workings of Artificial Intelligence — and it’s here to stay. [https://towardsdatascience.com/5-ways-mother-nature-inspires-artificial-intelligence-2c6700bb56b6 5 Ways mother nature inspires artificial intelligence | Luke James - Towards Data Science] |
Revision as of 19:26, 19 August 2023
YouTube search... ...Google search
- Symbiotic Intelligence ... Bio-inspired Computing ... Neuroscience ... Connecting Brains ... Nanobots ... Molecular ... Neuromorphic ... Evolutionary/Genetic
- Collective Animal Intelligence ... Animal Ecology ... Animal Language ... Bird Identification
- History of Artificial Intelligence (AI) ... Creatives
- Lifelong Learning - Catastrophic Forgetting Challenge
- Other Challenges in Artificial Intelligence
- AI Solver ... Algorithms ... Administration ... Model Search ... Discriminative vs. Generative ... Optimizer ... Train, Validate, and Test
- 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
- An AI Experiment Generated 40,000 Hypothetical Bioweapons in Just 6 Hours | David Nield - Science Alert
Bio-inspired Computing is a subset of metaphor-based metaheuristics
Bio-inspired AI or Nature-inspired AI is a branch of artificial intelligence that seeks to develop intelligent agents by mimicking the behavior of natural systems. The world of AI has a lot of things around it to thank for its existence in our technological landscape of today. Not only have humans spent decades of research perfecting the mathematical calculations to make these wonderfully complex learning algorithms work but during this time we have looked further than our own species as inspiration to make the next generation of intelligent presence on our planet. Mother Nature, and all that it encompasses, has it’s roots firmly planted in the workings of Artificial Intelligence — and it’s here to stay. 5 Ways mother nature inspires artificial intelligence | Luke James - Towards Data Science
- Bacterial Foraging Optimization Algorithm | Jason Brownlee
- Bat algorithm | Wikipedia
- Bees
- Biodegradability Prediction | Wikipedia
- Neuroscience - brain architecture - Cognitive Brain Function (Neurons) - Neural Network
- Cells
- Classical/Pavlov Conditioning - Reinforcement Learning (RL)
- Cuckoo Search | Wikipedia
- Cuttlefish Optimization Algorithm | Wikipedia
- Epidemiology of Infectious Disease (networks) | L. Danon, A.P. Ford, T. House, C.P. Jewell, M. Keeling, G.O. Roberts, J.V. Ross, and M.C. Vernon
- Collective Animal Intelligence:
- Flocking (birds) | Wikipedia
- Ant Colony Optimization Algorithms (insects) | Wikipedia
- DARPA Thinks Insect Brains Might Hold the Secret to Next-Gen AI (insects) | Nextgov
- Swarm intelligence (insects) | Wikipedia
- Particle Swarm Optimization | Wikipedia
- Shoaling & Schooling (fish) | Wikipedia
- Herd Behavior (land animals) | Wikipedia
- Evolution Strategy | Wikipedia
- Excitable Media; forest fires, "the wave", heart conditions, axons | Wikipedia
- Firefly Algorithm | Wikipedia
- Fish School Search | Wikipedia
- Fly Algorithm | Wikipedia
- {Leaping} Frog | R. Shivakumar, P.Tamilarasu and M.Panneerselvam
- Genetic Algorithm | Wikipedia - Survival of the Fittest/Evolution
- Grafting (decision trees) | Wikipedia
- (Artificial) Immune System
- (Artificial) Plant Optimization Algorithm | Wikipedia
- Plant Structures | Wikipedia
- Sensory Organs | Wikipedia
Swarm
One of the most well-known examples of nature-inspired AI is swarm intelligence.
Swarm intelligence is a type of collective behavior that emerges from the interactions of simple agents. Swarm intelligence is a rapidly growing field of research, and there are many new and exciting applications being developed all the time. As our understanding of swarm intelligence continues to grow, we can expect to see even more innovative and practical applications in the years to come. These agents are often autonomous and have limited capabilities, but they can achieve complex tasks by working together. Some examples of swarms in nature include flocks of birds, schools of fish, and colonies of ants.
The advantages of swarm intelligence include:
- It is scalable. Swarms can be made up of a large number of agents, which makes them well-suited for solving problems that are too complex for a single agent to solve.
- It is robust. Swarms can continue to function even if some of the agents are lost or damaged.
- It is adaptive. Swarms can learn and adapt to changes in their environment.
Some of the applications of swarm intelligence include:
Here are some specific examples of the advantages of swarm intelligence in real-world applications:
- In robotics, swarms of robots can be used to perform tasks that are too dangerous or difficult for humans, such as defusing bombs or exploring hazardous environments.
- In traffic control, swarm intelligence can be used to optimize traffic flow and reduce congestion. This can be done by using sensors to monitor traffic conditions and then adjusting the speed and direction of vehicles in real time.
- In financial trading, swarm intelligence can be used to make trading decisions and predict market trends. This can be done by using historical data to train a swarm of agents to identify patterns in the market.
- In data mining, swarm intelligence can be used to find patterns in large datasets. This can be done by using swarm agents to explore the dataset and identify clusters of data that are similar to each other.
