How Researchers Use Diagrams in Communicating Neural Network Systems
- URL: http://arxiv.org/abs/2008.12566v2
- Date: Mon, 31 Aug 2020 09:59:39 GMT
- Title: How Researchers Use Diagrams in Communicating Neural Network Systems
- Authors: Guy Clarke Marshall, Andr\'e Freitas, Caroline Jay
- Abstract summary: This paper reports on a study into the use of neural network system diagrams.
We find high diversity of usage, perception and preference in both creation and interpretation of diagrams.
Considering the interview data alongside existing guidance, we propose guidelines aiming to improve the way in which neural network system diagrams are constructed.
- Score: 5.064404027153093
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Neural networks are a prevalent and effective machine learning component, and
their application is leading to significant scientific progress in many
domains. As the field of neural network systems is fast growing, it is
important to understand how advances are communicated. Diagrams are key to
this, appearing in almost all papers describing novel systems. This paper
reports on a study into the use of neural network system diagrams, through
interviews, card sorting, and qualitative feedback structured around
ecologically-derived examples. We find high diversity of usage, perception and
preference in both creation and interpretation of diagrams, examining this in
the context of existing design, information visualisation, and user experience
guidelines. Considering the interview data alongside existing guidance, we
propose guidelines aiming to improve the way in which neural network system
diagrams are constructed.
Related papers
- Coding schemes in neural networks learning classification tasks [52.22978725954347]
We investigate fully-connected, wide neural networks learning classification tasks.
We show that the networks acquire strong, data-dependent features.
Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
arXiv Detail & Related papers (2024-06-24T14:50:05Z) - Reviewing Developments of Graph Convolutional Network Techniques for
Recommendation Systems [1.2277343096128712]
We try to review recent literature on graph neural network-based recommender systems.
We explore the motivation behind incorporating graph neural networks into recommender systems.
arXiv Detail & Related papers (2023-11-10T12:11:36Z) - Graph Neural Operators for Classification of Spatial Transcriptomics
Data [1.408706290287121]
We propose a study incorporating various graph neural network approaches to validate the efficacy of applying neural operators towards prediction of brain regions in mouse brain tissue samples.
We were able to achieve an F1 score of nearly 72% for the graph neural operator approach which outperformed all baseline and other graph network approaches.
arXiv Detail & Related papers (2023-02-01T18:32:06Z) - Neuro-symbolic computing with spiking neural networks [0.6035125735474387]
We extend previous work on spike-based graph algorithms by demonstrating how symbolic and multi-relational information can be encoded using spiking neurons.
The introduced framework is enabled by combining the graph embedding paradigm and the recent progress in training spiking neural networks using error backpropagation.
arXiv Detail & Related papers (2022-08-04T10:49:34Z) - TeKo: Text-Rich Graph Neural Networks with External Knowledge [75.91477450060808]
We propose a novel text-rich graph neural network with external knowledge (TeKo)
We first present a flexible heterogeneous semantic network that incorporates high-quality entities.
We then introduce two types of external knowledge, that is, structured triplets and unstructured entity description.
arXiv Detail & Related papers (2022-06-15T02:33:10Z) - Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs.
By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
arXiv Detail & Related papers (2022-02-01T17:11:13Z) - Learning through structure: towards deep neuromorphic knowledge graph
embeddings [0.5906031288935515]
We propose a strategy to map deep graph learning architectures for knowledge graph reasoning to neuromorphic architectures.
Based on the insight that randomly and untrained graph neural networks are able to preserve local graph structures, we compose a frozen neural network shallow knowledge graph embedding models.
We experimentally show that already on conventional computing hardware, this leads to a significant speedup and memory reduction while maintaining a competitive performance level.
arXiv Detail & Related papers (2021-09-21T18:01:04Z) - Network representation learning systematic review: ancestors and current
development state [1.0312968200748116]
We present a systematic survey of network representation learning, known as network embedding, from birth to the current development state.
We provide also formal definitions of basic concepts required to understand network representation learning.
Most commonly used downstream tasks to evaluate embeddings, their evaluation metrics and popular datasets are highlighted.
arXiv Detail & Related papers (2021-09-14T14:44:44Z) - Learning Contact Dynamics using Physically Structured Neural Networks [81.73947303886753]
We use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects.
We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations.
Our results indicate that an idealised form of touch feedback is a key component of making this learning problem tractable.
arXiv Detail & Related papers (2021-02-22T17:33:51Z) - Graph-Based Neural Network Models with Multiple Self-Supervised
Auxiliary Tasks [79.28094304325116]
Graph Convolutional Networks are among the most promising approaches for capturing relationships among structured data points.
We propose three novel self-supervised auxiliary tasks to train graph-based neural network models in a multi-task fashion.
arXiv Detail & Related papers (2020-11-14T11:09:51Z) - Graph Structure of Neural Networks [104.33754950606298]
We show how the graph structure of neural networks affect their predictive performance.
A "sweet spot" of relational graphs leads to neural networks with significantly improved predictive performance.
Top-performing neural networks have graph structure surprisingly similar to those of real biological neural networks.
arXiv Detail & Related papers (2020-07-13T17:59:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.