Artificial Neural Nets and the Representation of Human Concepts
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913284371775488 |
|---|---|
| author | Freiesleben, Timo |
| author_facet | Freiesleben, Timo |
| contents | What do artificial neural networks (ANNs) learn? The machine learning (ML) community shares the narrative that ANNs must develop abstract human concepts to perform complex tasks. Some go even further and believe that these concepts are stored in individual units of the network. Based on current research, I systematically investigate the assumptions underlying this narrative. I conclude that ANNs are indeed capable of performing complex prediction tasks, and that they may learn human and non-human concepts to do so. However, evidence indicates that ANNs do not represent these concepts in individual units. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_05337 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Artificial Neural Nets and the Representation of Human Concepts Freiesleben, Timo Machine Learning Artificial Intelligence What do artificial neural networks (ANNs) learn? The machine learning (ML) community shares the narrative that ANNs must develop abstract human concepts to perform complex tasks. Some go even further and believe that these concepts are stored in individual units of the network. Based on current research, I systematically investigate the assumptions underlying this narrative. I conclude that ANNs are indeed capable of performing complex prediction tasks, and that they may learn human and non-human concepts to do so. However, evidence indicates that ANNs do not represent these concepts in individual units. |
| title | Artificial Neural Nets and the Representation of Human Concepts |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2312.05337 |