Lecture notes: From Gaussian processes to feature learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908833261027328 |
|---|---|
| author | Helias, Moritz Lindner, Javed Schutzeichel, Lars Ringel, Zohar |
| author_facet | Helias, Moritz Lindner, Javed Schutzeichel, Lars Ringel, Zohar |
| contents | These lecture notes develop the theory of learning in deep and recurrent neuronal networks from the point of view of Bayesian inference. The aim is to enable the reader to understand typical computations found in the literature in this field. Initial chapters develop the theoretical tools, such as probabilities, moment and cumulant-generating functions, and some notions of large deviation theory, as far as they are needed to understand collective network behavior with large numbers of parameters. The main part of the notes derives the theory of Bayesian inference for deep and recurrent networks, starting with the neural network Gaussian process (lazy-learning) limit, which is subsequently extended to study feature learning from the point of view of adaptive kernels. The notes also expose the link between the adaptive kernel approach and approaches of kernel rescaling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12855 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Lecture notes: From Gaussian processes to feature learning Helias, Moritz Lindner, Javed Schutzeichel, Lars Ringel, Zohar Disordered Systems and Neural Networks These lecture notes develop the theory of learning in deep and recurrent neuronal networks from the point of view of Bayesian inference. The aim is to enable the reader to understand typical computations found in the literature in this field. Initial chapters develop the theoretical tools, such as probabilities, moment and cumulant-generating functions, and some notions of large deviation theory, as far as they are needed to understand collective network behavior with large numbers of parameters. The main part of the notes derives the theory of Bayesian inference for deep and recurrent networks, starting with the neural network Gaussian process (lazy-learning) limit, which is subsequently extended to study feature learning from the point of view of adaptive kernels. The notes also expose the link between the adaptive kernel approach and approaches of kernel rescaling. |
| title | Lecture notes: From Gaussian processes to feature learning |
| topic | Disordered Systems and Neural Networks |
| url | https://arxiv.org/abs/2602.12855 |