Viewing profile — nothing0001

I find a little sad that many people could change books and sharing experiences with others with using tools such as chatgpt. Those tools could be used to not discuss things like e…

How can they avoid that someone perform a post-training from this model to obtain a different model that perhaps could not be protected by copyright?

I think you are absolutely right, but those sames problems apply when the paper claim that the average of two models gives a good model. So in that case the weight space could have…

A negative value cannot be produced but in the hidden layers the output of one neuron is multiplied by weights so the sign can be encoded in those weights.

Reading the paper, I was thinking about the following: Given the weights of two models w1 and w2, then at each neuron k compute some average of the absolute difference of the outpu…

I wonder what happens when one change the activation function, is there some related results in that direction?

I asked chatgpt to generate the different orders of 5 words, it failed at it. Then I ask it to generalize the problem and then it refers to permutations (giving the formula). Then …

Now that I am interested in large language model and as I begin reading Street Fighting Mathematics, the first thought is that large language model can learn a lot (statistical app…

It seems I used a lot of prompts: Some of them follow. Define the projection of word1 with respect to word2 as a word that is has a similar meaning to word1 and word2 and that is u…

r(man,young,age,old) r(man,rich, wealth, poor) now find w2 and w4 for r(_, creative,_, unordered) Here's a revised relation with the words more similar to "creative" in the second …

Just make a loss function that gives +1 for correct answer, -1 for incorrect answers and 0 for unknown. Since this idea took me like 10 seconds, I suppose something like this must/…