Why do the peaks on the learning graph keep changing?
Up to 5000 graph points are recorded. This is sufficient for over 200,000,000 learning cycles. The graph is produced by sampling these points. The horizontal axis is non linear to allow the whole learning progress to be displayed regardless of the number of cycles executed. As more cycles are executed the graph is squashed to the left. This means that the samples of the graph points are not identical every time that the graph is updated. Some short term peaks may miss the sampling and appear to change. This sampling is related to the display performance. It would take a long time to redraw the graph and include every one of the 5000 points.
Related Questions
- Could you explain again the graph/animation of the microlensing? What is happening at the peaks when the star appears bright?
- How do the standards reflect emerging technologies that are changing teaching and learning in our schools?
- What is a transformation that slides a graph without changing the size or shape?
