for calculating tariff prices
by Andrew Ng
5 courses
~80 hours of videos + coding
30 euro / month
3rd party service
3 months, 331726 entries
- Warren McCulloch and Walter Pitts (1943) -
created a computational model for neural networks
- Ramón y Cajal, Santiago (1899).
Comparative study of the sensory areas of the human cortex.
- Frank Rosenblatt build Mark I Perceptron in 1960
- Universal approximation theorem
(proved by George Cybenko in 1989)
{ "input": { "familyStatus": "Keine Angabe", "educationType": "Berufsausbildung", "jobSituation": "Angestellt/Selbstständig", "industry": "Sonstige Branche", "benefitAgeLimit": 60, "benefitAmount": 1000, "fractionOfficeWork": 100, "staffResponsibility": 0, "smoker": false, "birthday": "1983-11-07", "insuranceStart": "2018-12-01" }, "output": { "exists": true, "net": 92.05 } }
Enum, 6500 options, actually ~ 6 risk groups
Enum, 4 options
Enum, 9 options
Enum, 3 options
Enum, 10 options
Number
Boolean
Date
"occupation": "Isolierer,in",
single node,
a real number 0..1
(the presence problem)
41 input nodes
The code itself is here:
https://github.com/pavelgit/ml-techtalk
or here:
https://bitbucket.check24.de/users/pavel.liubinski/repos/ml-techtalk-2019/browse
Questions remaining
By Pavel L
