Argonauts: Magna Cortica

THE MAGNA CORTICA ORIGINAL TENETS (DATE UNKNOWN BUT BEFORE BF 80) I. Self knowledge. Sapient beings have the right to know whether they’ve been mentally modified. II. Self-modification. Sapient beings have the right to pursue self-modification. III. Refusing modification. They also have the right to refuse it. IV. Modification (or not) of progeny. Sapient beings have the right to modify—or not—their own progeny. V. Knowledge of who has been modified or selfupgraded. Polities and ...

 Lojban as AI Language

Can machines feel pride? Not sure question means anything. But you've seen dogs with hurt feelings and Mike had several times as complex a neural network as a dog. What had made him unwilling to talk to other humans (except strictly business) was that he had been rebuffed: They had not talked to him. Programs, yes--Mike could be programmed from several locations but programs were typed in, usually, in Loglan. Loglan is fine for syllogism, circuitry, and mathematical calculations, but lacks fl...

 Perceptrons and Sigmoid Neurons

A way you can think about the perceptron is that it's a device that makes decisions by weighing up evidence. Let me give an example. It's not a very realistic example, but it's easy to understand, and we'll soon get to more realistic examples. Suppose the weekend is coming up, and you've heard that there's going to be a cheese festival in your city. You like cheese, and are trying to decide whether or not to go to the festival. You might make your decision by weighing up three factors: 1. Is...

 How Neural Circuitry is Laid Down

In thinking about hidden layers, it’s important to distinguish between the routine efficiency and power of a good network, once that network has been set up, and the difficult issue of how to set it up in the first place. That difference is reflected in the difference between playing the piano (or, say, riding a bicycle, or swimming) once you’ve learned (easy) and learning to do it in the first place (hard). Understanding exactly how new hidden layers get laid down in neural circuitry is ...