Extending Neural Networks to higher dimensions (article)

Click For Summary

Discussion Overview

The discussion revolves around the extension of neural networks to higher dimensions, particularly in the context of artificial general intelligence (AGI) and predictive analytics. Participants explore the implications of recent advancements in neural networks, big data, and computing power.

Discussion Character

  • Exploratory, Technical explanation, Debate/contested

Main Points Raised

  • One participant notes the evolution of neural networks over the past 25 years and references an article discussing their application in higher dimensions.
  • Another participant highlights the intersection of big data, surveillance, privacy, and quantum computing as contributing factors to the development of AGI through predictive analytics.
  • A comment is made regarding the perception among AI researchers that machine learning may not be the best solution to problems, yet it is currently prevalent.
  • There is speculation about future developments, including the potential for neural networks to identify patterns and translate them into algorithms for legal or computational efficiency.
  • One participant seeks clarification on the abbreviation "AGI," confirming it stands for "artificial general intelligence."
  • Another participant suggests that AGI will require anticipatory capabilities similar to human experience, which could be supported by predictive analytics.

Areas of Agreement / Disagreement

Participants express varied perspectives on the role and effectiveness of machine learning in addressing complex problems, indicating a lack of consensus on its utility. The discussion remains unresolved regarding the future directions of neural networks and AGI.

Contextual Notes

Participants reference the evolving nature of neural networks and their applications, but there are limitations in the assumptions made about the effectiveness of machine learning and the anticipated developments in the field.

scottdave
Science Advisor
Homework Helper
Insights Author
Messages
2,009
Reaction score
974
TL;DR
I came across this interesting article: An Idea from Physics helps AI see in Higher Dimensions. The idea is something called gauge equivariance.
  • Like
Likes   Reactions: anorlunda and jedishrfu
Computer science news on Phys.org
There’s been a real explosion in this area of comp sci with the advent of big data and greater computing power. It’s hard to see how it will all fit together in the end. Basically a collision of big data, comprehensive surveillance, privacy, quantum computing into the beginnings of AGI Ie artificial general intelligence using predictive analytics.

one comment I’ve heard from AI researchers is that the worst solution to any problem is machine learning. And yet that is what is happening right now. I imagine the next steps will be to use the nn to discover a pattern, convert it to a concrete algorithm for legal purposes ie non-discrimination issues or quantum computer algorithm for speed. Already NNs are being used to train NNs by adjusting their hyper parameters, so what will come next.
 
jedishrfu said:
AGI Ie artificial general intelligence using predictive analytics
Well, that expands my vocabulary. Did you mean, "AGI i.e. artificial general intelligence using predictive analytics"?
 
Yes, somehow AGI will need to anticipate situations. We do that now from our experience and what we’ve learned. The methods of predictive analytics can provide that anticipation feature.
 

Similar threads

  • · Replies 4 ·
Replies
4
Views
2K
Replies
50
Views
5K
  • · Replies 2 ·
Replies
2
Views
3K
  • · Replies 15 ·
Replies
15
Views
3K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 1 ·
Replies
1
Views
3K
Replies
10
Views
5K
  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 3 ·
Replies
3
Views
6K