Maikel van de Lisdonk 2024-08-25 11:22:57 I've made some visualization improvements for the neural network layer nodes in my visual programming system "code flow canvas". Nodes can now have meta information to show internal data which is stored on the node level that is not shown on the node itself. For the neural network nodes this are the weights and biases.
Also the structure of the neural network itself can be viewed in a scalable way instead of just the nodes on the canvas itself. And with scalable I mean not showing all the nodes, but only a max of 10 per layer and add smaller dots in between to illustrate that there are more nodes then just the max 10 that are shown per layer. The number of dots are different depending on the total node count to make it clear that layers differ in total node count.
You can see it here: youtu.be/dvZrWEz1W4k or try it yourself at demo.codeflowcanvas.io and select the neural network mnist training & testing example.
Kartik Agaram 2024-08-28 19:03:30 Leveling up goals: a shower thought
Konrad Hinsen 2024-08-29 08:55:00 "Create a system that can outlives you" applies to much more than just bureaucracies. It's also true of culture, and of everything in between bureaucracy and culture in terms of intentionality (bureaucracy is set up intentionally, culture emerges).
One example of "in between" is capitalism, which is encoded in tons of laws and contracts, but neither supervised by a bureaucracy created for that purpose, nor an accident of history that nobody planned for.
Kartik Agaram 2024-08-29 20:27:53 It is interesting to contrast bureaucracy with culture. The part that's unique to bureaucracy is: the system outlives its own usefulness. Because it was created by a central group of people and imposed along a power differential.
Software is just bureaucracy by other means.
Capitalism is emergent, but capitalism is fundamentally designed to encourage firms which are not emergent but built along a power differential. Firms are bureaucracies.
Konrad Hinsen 2024-08-30 06:38:37 Culture can also outlive its own usefulness, by becoming ill-adapted to a changing environment. Example: the traditional European gender roles were just basic common sense for centuries of mostly agrarian life. Then the industrial revolution happened, and now they are just some weird tradition.
