1 / 15

Artificial Intelligence for Environmental Applications

Artificial Intelligence for Environmental Applications. Fabio Scotti University of Milan. Artificial Intelligent Systems. We can debate endlessly about whether a certain system is intelligent or not … SW programs or SW/HW systems designed to perform complex tasks

armbruster
Download Presentation

Artificial Intelligence for Environmental Applications

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Artificial Intelligence for Environmental Applications Fabio Scotti University of Milan The 2018 GEO Symposium, 11-12 June 2018, Geneva, Switzerland

  2. Artificial Intelligent Systems • We can debate endlessly about whether a certain system is intelligent or not … • SW programs or SW/HW systems designed • to perform complex tasks • employing strategies that mimic some aspect of human thought • the key is evolution: it is intelligent if it can learn (even if only a limited sense) and/or get better in time

  3. Artificial Intelligence (AI) vs Machine learning (ML) AI: is the broader concept of machines being able to carry out tasks in a way that we would consider “smart”. ML: an application of AI based around the idea that we should really just be able to give machines access to data and let them learn for themselves.

  4. ML in a metaphor It’s like gardening • Seeds = Algorithms • Nutrients = Data • Gardener = You • Plants = Programs/ trained models

  5. Not for all applications.. • IF • the nature of computations required in a task is not well understood • or there are too many exceptions to the rules • or known algorithms are too complex or inefficient • THEN • AI can be considered as a possible solution

  6. Computational intelligence According to Engelbrecht (2006) Theory, design, application, and development of biologically and linguistically motivated computational paradigms

  7. Traditional and Deep Learning networks

  8. Traditional ML vs Deep Learning Convolutional Neural Networks

  9. Classical ML vs DeepLearning (classical) DL needs data….

  10. Three main drivers for AI and Algorithms Especially for Deep Learn

  11. The 4th driver • The designer • A priori knowledge • Data selection • Data Filtering and Enhancing • Model selection • Learning technique choice • Experiment Design • Avoid brute force • Hybrid systems • Dividi et impera

  12. AI in Environmental Applications • From 2D (RBG) image to Sensor data, Heterogeneous Data (hyperspectral, LiDAR, etc.) • Sensors and Measurement systems,Signal processing, Image processing, Sensor Data Fusion, Classification and Clustering

  13. Artificial Intelligence in Environmental Applications Fuzzy Systems Smarter Intelligent Adaptive Neural Networks Evolvable Evolutionary Computing

  14. Composite Systems TRADITIONAL PARADIGMS +COMPUTATIONAL INTELLIGENCE =_________________________________+ MORE DESIGN DEGREES OF FREEDOM+ ACCURACY + PERFORMACE Neural Network FuzzyAlgorithm Output Input Filter DesignerRoutine

  15. Conclusions • Artificial intelligence offers additional opportunities for adaptable and evolvable systems for environmental applications • Avoid black box approaches without considering alternatives • Deep learning is not the solution for all applications • A comprehensive design methodology should deal with all aspects in an integrated way

More Related