FROM BIG DATA TO SMALL ROBOTS CURRENT TRENDS OF AI AND OUR PLACE - PowerPoint PPT Presentation

FROM BIG DATA TO SMALL ROBOTS CURRENT TRENDS OF AI AND OUR PLACE AS HUMAN USERS ERIK BILLING – UNIVERSITY OF SKÖVDE Bild 1 Bild 1 U N I V E R S I T Y O F S K Ö V D E – W W W . H I S . S E / E N

Bild 2 Bild 2

Bild 3 Bild 3

Bild 4

Goals and methodology 3/4 19 September 2019 5 Bild 5

19 September 2019 6 Robot assisted therapy “ In DREAM We are taking this further Bild 6 19 September 2019 6

19 September 2019 7 Research questions 1. Is this a good method for treating children with autism? 2. Technical aspects 1. Sense signals from the child 2. Detect what the child is doing 3. Make the robot react in a suitable way 4. Define subjective notions of “attention” and “imitation” so that the robot can understand? Cao et al. (2019) IEEE Robotics & Automation Bild 7 Erik Billing, www.his.se/erikb 7

19 September 2019 8 In sum Ø AI is used to interpret and assess children's behaviour, and to control the robot Ø The system is designed with detailed input from clinicians as a tool for therapists Ø This is possibly only close collaboration between therapists and engineers Bild 8 Erik Billing, www.his.se/erikb 8

DEEP LEARNING FOR DRUG DESIGN Generation of new compounds that have attractive properties Minimal side Efficacious Safe effects On molecular level Polar surface molecular weight Lipophilicity area (PSA) (MW) (clogP) Bild 12 Erik Billing, www.his.se/erikb Sthål et al. (2019) J. Chem. Inf. Model.

DEEP LEARNING FOR DRUG DESIGN Bild 13 Erik Billing, www.his.se/erikb Sthål et al. (2019) J. Chem. Inf. Model.

DEEP LEARNING FOR DRUG DESIGN Bild 14 Erik Billing, www.his.se/erikb Sthål et al. (2019) J. Chem. Inf. Model.

DEEP LEARNING FOR DRUG DESIGN (b) clogP ) Molecular weight (b) clogP (a) Molecular weight (c) PSA distribution of molecular properties in the original dataset Bild 15 Erik Billing, www.his.se/erikb Sthål et al. (2019) J. Chem. Inf. Model. s that are generated in the last 10 epochs (red). The target

INFOFUSION FUSARIUM Prediction of fungal infestation on oat Bild 16 Erik Billing, www.his.se/erikb

Bild 17 17

FARMERS’ SITUATED KNOWLEDGE We recomment that the “role of advisors and AgriDSS in advisory situations is reconsidered, changing from focusing on decision-making events/outputs towards thinking in terms of learning how to improve farmers situated seeing, and care” Bild 18 Erik Billing, www.his.se/erikb Lundström & Lindblom (2018) J. Agr. Sys.

NEXT STEPS Design by AI • Decision support in design • Drug design, Industrial settings, ergonomics Open AI • Data privacy • Data lock in Interaction with intelligent systes • Transparent and Explainable AI • User Experience Design Bild 23 Erik Billing, www.his.se/erikb

19 September 2019 24 Tack! • https://www.his.se/en/sail/ • https://www.his.se/en/Research /informatics/Interaction-Lab/ Bild 24 Erik Billing, www.his.se/erikb 24