Hopfield model with planted patterns: a teacher-student self-supervised learning model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916077331546112 |
|---|---|
| author | Alemanno, Francesco Camanzi, Luca Manzan, Gianluca Tantari, Daniele |
| author_facet | Alemanno, Francesco Camanzi, Luca Manzan, Gianluca Tantari, Daniele |
| contents | While Hopfield networks are known as paradigmatic models for memory storage and retrieval, modern artificial intelligence systems mainly stand on the machine learning paradigm. We show that it is possible to formulate a teacher-student self-supervised learning problem with Boltzmann machines in terms of a suitable generalization of the Hopfield model with structured patterns, where the spin variables are the machine weights and patterns correspond to the training set's examples. We analyze the learning performance by studying the phase diagram in terms of the training set size, the dataset noise and the inference temperature (i.e. the weight regularization). With a small but informative dataset the machine can learn by memorization. With a noisy dataset, an extensive number of examples above a critical threshold is needed. In this regime the memory storage limits of the system becomes an opportunity for the occurrence of a learning regime in which the system can generalize. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_13710 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Hopfield model with planted patterns: a teacher-student self-supervised learning model Alemanno, Francesco Camanzi, Luca Manzan, Gianluca Tantari, Daniele Disordered Systems and Neural Networks Machine Learning Mathematical Physics While Hopfield networks are known as paradigmatic models for memory storage and retrieval, modern artificial intelligence systems mainly stand on the machine learning paradigm. We show that it is possible to formulate a teacher-student self-supervised learning problem with Boltzmann machines in terms of a suitable generalization of the Hopfield model with structured patterns, where the spin variables are the machine weights and patterns correspond to the training set's examples. We analyze the learning performance by studying the phase diagram in terms of the training set size, the dataset noise and the inference temperature (i.e. the weight regularization). With a small but informative dataset the machine can learn by memorization. With a noisy dataset, an extensive number of examples above a critical threshold is needed. In this regime the memory storage limits of the system becomes an opportunity for the occurrence of a learning regime in which the system can generalize. |
| title | Hopfield model with planted patterns: a teacher-student self-supervised learning model |
| topic | Disordered Systems and Neural Networks Machine Learning Mathematical Physics |
| url | https://arxiv.org/abs/2304.13710 |