Urgent.News

What's breaking now, across thousands of outlets.

AI

The Emergent Symbolic Structure of Artificial Neural Networks

Modern systems in artificial intelligence (AI) somehow excel in domains for which they seem poorly suited. Intelligence has traditionally been modeled as operating over structured combinations of symbols, such as logical formulas. However, the strongest modern AI systems are based on neural networks, which instead represent information in continuous vectors. Vectors seem inadequate for capturing…

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

More in AI

Your models agreed with each other. They were agreeing with themselves.

There is a small art project in our house that encodes a sentence as nothing but its word lengths. Each word becomes a run of some symbol, repeated once per letter; the symbol itself is chosen at…

  • Readings of same encoded message agreed more than chance would predict in first experiment.
  • Second experiment showed reversed agreement, highlighting deception by baselines.
  • Researchers emphasized importance of using correct competitor for accurate agreement measurement.

More from Sunday 30 August →