Visualizing Learning and Computation in Artificial Neural Networks

By Mark W. Craven, Jude W. Shavlik. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Paulo Cortez
2. Mengchen Liu
3. Shixia Liu
4. Giulia Vilone
5. Mark J. Embrechts
6. Longo Luca
7. Jun Zhu
8. Xiting Wang

Citations in the corpus

• Opening black box Data Mining models using Sensitivity Analysis (2011, methodology): “Turning to visualization techniques, several graphical methods were proposed, such as: Hinton and Bond diagrams for NN [11]; showing NN weights and classification uncertainty [12]; and improving the interpretability of kernel-based classification methods [13].”
• Towards better analysis of machine learning models: A visual analytics perspective (2017, methodology): “Network-based techniques [23, 24, 25] solve this problem by displaying the network topology.”
• A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, methodology): “The mentioned exemplary rule-extraction methods DeepRED [152] and VIA [130], as well as decision tree extractors TRE- PAN [32], Concept Tree [111] and C4.5 [108] all provide global, rule-based output.”
• Opening the black box - data driven visualization of neural networks (2005, background): “Craven and Shavlik [5] surveyed a number of visualization techniques for understanding the learning and decision-making processes of neural networks, including Hinton diagrams, bond diagrams, hyperplane diagrams, response-function plots, and trajectory diagrams.”
• An Interactive Node-Link Visualization of Convolutional Neural Networks (2015, background): “explore the layer-by-layer output of a network, and build intuitions about how neural networks perform hierarchical abstraction from input to output [5].”
• Explainable Artificial Intelligence: a Systematic Review (2020, background): “Explanators generating salient masks were investigated in [20, 30] whilst [20, 39] reviewed methods that graphically represent the inner structure and functioning of neural networks with flow-charts or other explanatory graphs.”
• Using sensitivity analysis and visualization techniques to open black box data mining models (2013, background): “There is a wide range of “black box” supervised DM methods, which are capable of accurate predictions, but where obtained models are too complex to be easily understood by humans.”
• Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers (2018, unknown): “However, visualization research for neural network started well before [11], [12], [13].”
• Visualization of learning in multilayer perceptron networks using principal component analysis (2003, background): “Such displays are sometimes called response function plots [5].”