Intelligence at the Edge of Chaos
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929737141583872 |
|---|---|
| author | Zhang, Shiyang Patel, Aakash Rizvi, Syed A Liu, Nianchen He, Sizhuang Karbasi, Amin Zappala, Emanuele van Dijk, David |
| author_facet | Zhang, Shiyang Patel, Aakash Rizvi, Syed A Liu, Nianchen He, Sizhuang Karbasi, Amin Zappala, Emanuele van Dijk, David |
| contents | We explore the emergence of intelligent behavior in artificial systems by investigating how the complexity of rule-based systems influences the capabilities of models trained to predict these rules. Our study focuses on elementary cellular automata (ECA), simple yet powerful one-dimensional systems that generate behaviors ranging from trivial to highly complex. By training distinct Large Language Models (LLMs) on different ECAs, we evaluated the relationship between the complexity of the rules' behavior and the intelligence exhibited by the LLMs, as reflected in their performance on downstream tasks. Our findings reveal that rules with higher complexity lead to models exhibiting greater intelligence, as demonstrated by their performance on reasoning and chess move prediction tasks. Both uniform and periodic systems, and often also highly chaotic systems, resulted in poorer downstream performance, highlighting a sweet spot of complexity conducive to intelligence. We conjecture that intelligence arises from the ability to predict complexity and that creating intelligence may require only exposure to complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02536 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Intelligence at the Edge of Chaos Zhang, Shiyang Patel, Aakash Rizvi, Syed A Liu, Nianchen He, Sizhuang Karbasi, Amin Zappala, Emanuele van Dijk, David Artificial Intelligence Neural and Evolutionary Computing We explore the emergence of intelligent behavior in artificial systems by investigating how the complexity of rule-based systems influences the capabilities of models trained to predict these rules. Our study focuses on elementary cellular automata (ECA), simple yet powerful one-dimensional systems that generate behaviors ranging from trivial to highly complex. By training distinct Large Language Models (LLMs) on different ECAs, we evaluated the relationship between the complexity of the rules' behavior and the intelligence exhibited by the LLMs, as reflected in their performance on downstream tasks. Our findings reveal that rules with higher complexity lead to models exhibiting greater intelligence, as demonstrated by their performance on reasoning and chess move prediction tasks. Both uniform and periodic systems, and often also highly chaotic systems, resulted in poorer downstream performance, highlighting a sweet spot of complexity conducive to intelligence. We conjecture that intelligence arises from the ability to predict complexity and that creating intelligence may require only exposure to complexity. |
| title | Intelligence at the Edge of Chaos |
| topic | Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2410.02536 |