Structural Learning in Artificial Neural Networks: A Neural Operator Perspective
Authors: Kaitlin Maile, Luga Hervé, Dennis George Wilson
TMLR 2022 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this review, we provide a survey on structural learning methods in deep ANNs, including a new neural operator framework from a cellular neuroscience context and perspective, aimed at motivating research on this challenging topic. We then provide an overview of ANN methods which include structural changes within the neural operator framework in the learning process, characterizing each neural operator in detail and drawing connections to their biological counterparts. Finally, we present overarching trends in how these operators are implemented and discuss the open challenges in structural learning in ANNs. |
| Researcher Affiliation | Academia | Kaitlin Maile EMAIL IRIT, University of Toulouse Hervé Luga EMAIL IRIT, University of Toulouse Dennis G. Wilson EMAIL ISAE-SUPAERO, University of Toulouse |
| Pseudocode | No | The paper describes various algorithms and methods conceptually (e.g., 'continuous NAS', 'path-sampling NAS', 'pruning algorithms') but does not present any structured pseudocode or algorithm blocks with numbered steps in the main text. |
| Open Source Code | No | This paper is a survey and review of existing structural learning methods. It does not introduce a new methodology or model for which source code would typically be provided. Therefore, there are no statements or links regarding the release of open-source code by the authors for this specific work. |
| Open Datasets | No | This paper is a survey and does not conduct original experiments that would require specific datasets. It discusses datasets (e.g., 'image classification datasets', 'CIFAR-10', 'ImageNet') in the context of summarizing the literature it reviews, but it does not provide access information for datasets used in its own research. |
| Dataset Splits | No | As a survey paper, this work does not conduct original experiments requiring specific dataset splits. Therefore, no information on training/test/validation splits is provided. |
| Hardware Specification | No | This paper is a review and does not report on original experiments that would involve specific hardware. While it discusses the impact of hardware (e.g., GPUs) on ANN training in general, it does not specify any hardware used for its own research activities. |
| Software Dependencies | No | As a survey paper, this work does not describe experimental implementations requiring specific software dependencies with version numbers. |
| Experiment Setup | No | This paper is a review and analysis of existing literature on structural learning. It does not conduct its own experiments or present new models, thus there are no specific experimental setup details, hyperparameters, or training configurations described for this work. |