search

OpenRoberta / openroberta-lab

The programming environment »Open Roberta Lab« by Fraunhofer IAIS enables children and adolescents to program robots. A variety of different programming blocks are provided to program motors and sensors of the robot. Open Roberta Lab uses an approach of graphical programming so that beginners can seamlessly start coding. As a cloud-based application, the platform can be used without prior installation of specific software but runs in any popular browser, independent of operating system and device.
Apache License 2.0
124 stars 121 forks source link

xNN New Features - UI/UX discussion / suggestions #1584

Open Thorlogy opened 10 months ago

Thorlogy commented 10 months ago
  1. Change the color of the Frame (input training data set) from black to turquoise - like the frame of the sensor data view.
  2. Possibility to change the size of the window for entering training data (enlarge / reduce).
  3. Possibility to set random numbers only for weights (and not for biases)
Thorlogy commented 10 months ago
  1. If you are in the "Neuronal Networks Define" tab, the pop-up training data window should remain open as you enter the input data layer by layer.
  2. It could be very helpful to show the formulas (or the methodes?) used for the calculation of the training loss and for the calculation of the edge weights + bias?
Thorlogy commented 10 months ago
  1. It could be very helpful if you could easily record sensor data and then use it as training data. This could be done via an extra block in the NEPO programme, for example. You could make settings here,
    • which sensor
    • Data rate (i.e. every second)
    • Type of data (raw data, ...)
Thorlogy commented 9 months ago
  1. Labelling the axes - for the trainingsloss graphic