Downloaded 88 times
Uploaded byChetan Kumar S
Computational Intelligence and Applications
The document discusses emerging topics in computational intelligence and applications, focusing on machine learning, deep learning, and the distinctions between computational intelligence and artificial intelligence. It highlights the potential of these technologies in solving real-world problems, their applications in various fields like autonomous transport and fake news detection, and the importance of achieving general intelligence. The presentation includes insights on fuzzy logic, evolutionary computing, and the need for biologically motivated learning methods.
More Related Content
Similar to Computational Intelligence and Applications
Computational Intelligence and Applications
- 1. Computational Intelligence and Applications IEEEComputational Intelligence Society Bangalore Chapter Winter School On Emerging Topics in Computational Intelligence -Theory and Applications S Chetan Kumar Co-founder AiKaan
- 2. Topics covered ● MLis cutting-edge of AI ● DL is cutting-edge of cutting-edge ● Is tensorflow good playground for ANN? ● CI and AI will lead to GI ? ● Biologically motivated learnings are needed to solve real world problems !! Confused !!
- 4. Back propagated RNNwith Bayesian optimization can prevent Long Short-Term memory issues of gradient descent Explain me in simple terms !!
- 5. General Intelligence: toperform intellectual task that a human can Artifical Intelligence My long-term goal is to reach General Intelligence Com putational Intelligence
- 6. CI vs AI ComputationalIntelligence Artificial Intelligence Soft Computing techniques Hard computing techniques Follows fuzzy logic Follows binary logic Nature inspired models Based on mathematical models Can work inexact and incomplete data Not very effective Probabilistic results Deterministic results
- 7. Computational and ArtificialIntelligence Computational Intelligence Artificial Intelligence Fuzzy logic and others
- 8. Principles of ComputationalIntelligence Fuzzy Logic Probabilistic model Learning theory Evolutionary computing Artificial Intelligence Hybrid Techniques
- 9. Artificial Intelligence ● Softcomputing technique ● Machines trying to achieve general intelligence ● Machine learning is one of the technique ● Knowledge based system is one another ● ML has become more popular
- 10. AI and ML ArtificialIntelligence Machine learning Knowledge based systems
- 11.
- 12. AI, ML, DL Deeplearning Feature/ Representation learning Machine learning Artificial Intelligence Machine learning Feature/ Representational learning Deep Learning
- 13. Machine learning ● Basicmachine learning Eg Logistic regression ● Feature or Representational learning If there objects to be classified, which feature of the object should I use to classify Eg. Shallow auto encoders ● Deep Learning Hierarchical representational learning Use feature learning as one of the inner layer in a multilayer perceptrons
- 14. Deep learing Slide byYann LeCun, all rights reserved.
- 15. Fuzzy Logic ● Multivalued logic An adjective !, how pretty the girl is ● Many applications facial pattern recognition, air conditioners, washing machines, antiskid braking systems, transmission systems, vacuum cleaners,
- 16.
- 17. Evolutionary Computing ● Choosea set of solution for a problem ● Pass them through a performance testing (survival track) ● Best performing solutions reproduce (select fittest) ● Add random mutation
- 18. What can CItake up ? ● Mundane cognitive & intellectual tasks Like evolution, repetitive work, slow change ● Creative cognitive & intellectual tasks Like mutation, new genesis ● CI or machines can take up mundane tasks Remember how mechanical mundane tasks are done by machines
- 19. Few Applications ofCI ● Negotiation and Bargaining ● Judgmental transactions Judgmental insurance claim settlements ● Power Grid management ● Self operated factories ● Detection Fake News Generation is already done :-) ● Autonomous Transporting systems ● Self operated networks !!
- 20. Fake News ● Itis lot easier to create news ! And much easier to create a fake one!! ● Fake news can create havoc ● Fake news detection needs correlation of data from multiple source ● Looking at the sentiments ● Looking at environment/reaction
- 21.
- 22.
- 23. Autonomous transport ● Dowe really need a car ? I mean driver or pilot or captain ● Our transport systems (right from home till destination) must be autonomous system Err.. not like this :-)
- 24. Self operated networks ●Just plug in devices(equipments) and networks must be formed ● Should provide services as per application needs ● Should identify faults in network ● Must repair faults ● Must optimize it self
- 25. Thank You Chetan KumarS chetansk@aikaan.io @chetansk www.aikaan.io