SONN : What's Next ?

post by D饾湅 路 2022-01-09T08:15:32.386Z 路 LWGW3 comments

Quick recap of the previous post [LWGW] and the reactions, using an analogy:

Post:

I invented a new type of engine that run on water, based on a law of nature that has never been properly used so far. Here are all the details, and the plan to reproduce it yourself easily. It develops 990 hp with 5cm3. There are 2 parameters to adjust for various settings.

Reactions:

The same ones, on Facebook:

I have spent over 20,000 hours on this. In billing hours, that is more than 2 million.

Most of the research time was spent looking for technical improvements, as exhaustively as possible. There is none. Everything else will have to be built on top of this.

With this publication, I have, publicly, established prior art. I cannot go any further alone. Until the end of the year, I am the only one that as the possibility of patenting it (at IC level).

The first consequence of rationality should be consistency.

What should I do now ?

D饾湅

 

Freedom is priceless.

If only some work on it, it becomes expensive.

If everybody does, it becomes free.

I am a free man.

3 comments

Comments sorted by top scores.

comment by korin432022-01-10T19:07:55.230ZLW(p) 路 GW(p)

The original post has 46 comments, a score of +36, several people attempting ports to other languages and other data sets, and a bunch of philosophical/scientific discussion. It's annoying that some people were focused on perfromance, and not everyone is convinced, but I think that's about as good of a response as you could expect on LessWrong.

comment by philip_b (crabman)2022-01-09T11:28:26.959ZLW(p) 路 GW(p)

I see you're frustrated with reactions of LessWrongers. You want to convince us that your model is important. Here are three questions I don't know the answer to which affect how important I deem your model.

  1. How much novelty does it have compared to existing brain inspired machine learning models? Perhaps you can write a "Related Work" section like in academic articles to answer this question.
  2. If the answer to the first question is "there is a lot of novelty", what implications does this have? Why is it important?
  3. Are there likely to be practical benefits to using your kind of models instead of neural networks? I.e., are they likely to be faster on inference, cheaper to train, generalize better, or something else, if now research time was put into the study of them?

Apart from this question, I have a recommendation for you. Try to publish your work at a conference or in a journal. If the answer to the first question is at least "as much novelty as there is in a typical brain-inspired model article", I think your result is publishable given good results on PI-MNIST and PI-FashionMnist. However, it would probably be important to use another dataset that is inherently permutation invariant as a benchmark in order to impress reviewers. This'll give you prestige, satisfaction, etc. You can also visit a conference about brain-inspired ml or a workshop about brain-inspired ml at a large ml conference, present your work there and take to people. You can also try to find where such people hang out on the internet and take to them there though I expect there's no such public good place.

Replies from: D饾湅
comment by D饾湅2022-01-09T15:11:34.815ZLW(p) 路 GW(p)

This introduces a new paradigm. Read T.Kuhn. You cannot compare different paradigms.

Everything that matters is in the post. Read it; really.

What is needed next is engineering, ingenuity and suitable ICs, not maths. The IT revolution came from IT (coders) and ICs, not CS.

As for your recommendation, I have tried so many things over the past four years鈥 I posted here first to get to the source of one of the evidences; to no avail.

Good bye everyone

I am available through private messages