I’ve been saying this for about a year since seeing the Othello GPT research, but it’s nice to see more minds changing as the research builds up.
I’ve been saying this for about a year since seeing the Othello GPT research, but it’s nice to see more minds changing as the research builds up.
So somewhere in there I’d expect nodes connected to represent the Othello grid. They wouldn’t necessarily be in a grid, just topologically the same graph.
Then I’d expect millions of other weighted connections to represent the moves within the grid including some weightings to prevent illegal moves. All based on mathematics and clever statistical analysis of the training data. If you want to refer to things as tokens then be my guest but it’s all graphs.
If you think I’m getting closer to your point can you just explain it properly? I don’t understand what you think a neural network model is or what you are trying to teach me with Pythag.
The most efficient way for a neural network to predict Pythagorean results given inputs would be to reverse engineer a Pythagorean function within itself rather than simply trying to model statistical relationships between inputs and results. To effectively build a world model of Pythagorean calculation.
Training to autocomplete doesn’t mean that the way it achieves this is limited to any one approach or solution, and it would be useful to keep in mind that a neural network of unbounded size can model any possible function.
It wouldn’t reverse engineer anything. It would start by weighting neurons based on it’s training set of Pythagorean triples. Over time this would get tuned to represent Pythag in the form of mathematical graphs.
This is not “understanding” as most people would know it. More like a set of encoded rules.
Seems to me you are attempting to understand machine learning mathematics through articles.
That quote is not a retort to anything I said.
Look up Category Theory. It demonstrates how the laws of mathematics can be derived by forming logical categories. From that you should be able to imagine how a neural network could perform a similar task within its structure.
It is not understanding, just encoding to arrive at correct results.
What I quoted isn’t an article, it was a mathematics dissertation.
And you disputed that a NN could arrive at the theorem before being corrected about it.
There you go arguing in bad faith again by putting words in my mouth and reducing the nuance of what was said.
You do know dissertations are articles and don’t constitute any form or rigorous proof in and of themselves? Seems like you have a very rudimentary understanding of English, which might explain why you keep struggling with semantics. If that is so, I apologise because definitions are difficult when it comes to language, let alone ESL.
I didn’t dispute that NNs can arrive at a theorem. I debate whether they truly understand the theorem they have encoded in their graphs as you claim.
This is a philosophical/semantical debate as to what “understanding” actually is because there’s not really any evidence that they are any more than clever pattern recognition algorithms driven by mathematics.
Where did I claim that? Cite the exact phrase.
I said reverse engineer. Not deduce or prove.
Title of your post is literally “New Theory Suggests Chatbots Can Understand Text”.
You also hinted at it with your Pythag analogy.