Hacker Read top | best | new | newcomments | leaders | about | bookmarklet login

This is just based on unknown factors, and the difficulty of getting the dataset. But this do not stop the thing that taste of feeling can be expressed as a vector and that is its representation inside the neural network.

But then I think I get what you mean. Yeah the thing behind taste is a matrix, you multiply the current state of the body+food and it returns what you feel by your tongue. Since matrix modelize all kinds of interaction between all other factors. This should clears the problem.

But still the output is a vector. Taste is a vector. But different people can have different matrix to be multiplied with. In physics they call this kind of matrix "observable". If you know physics you get the idea.



view as:

Yeah, that makes more sense. I just wanted to point out that taste isn't just the input but also the experience of that input.

Then you could also argue that replicating human feelings or taste isn't very important, and it isn't really except if you want it to understand humans. I think it will be hard to understand humans well without also being able to predict their feelings or taste, we humans have that built in but a computer would need data to predict it.


Sounds like we are converging to a point that taste science is the next doable project in deep learning. Find something that can be measured. For example measure the amount of sweat of the person eating spicy food. The blood flood rate in the surface of skin. We can know roughly how the person react to spiciness. And than maybe do some clustering, changing the amount of spiciness, draw some regression curve, damn this is exciting!

Legal | privacy