• Corpus ID: 202565658

Illuminated Decision Trees with Lucid

@article{Mott2019IlluminatedDT,
  title={Illuminated Decision Trees with Lucid},
  author={David Mott and Richard J. Tomsett},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.05644}
}
The Lucid methods described by Olah et al. (2018) provide a way to inspect the inner workings of neural networks trained on image classification tasks using feature visualization. Such methods have generally been applied to networks trained on visually rich, large-scale image datasets like ImageNet, which enables them to produce enticing feature visualizations. To investigate these methods further, we applied them to classifiers trained to perform the much simpler (in terms of dataset size and… 

Figures from this paper

Deep learning-based object recognition in multispectral satellite imagery for real-time applications

TLDR
This work proposes a fully convolutional neural network architecture optimised for accurate and accelerated object recognition in multispectral satellite imagery, and shows that this FCN exceeds human-level performance with state-of-the-art 97.67% accuracy over multiple sensors.

References

SHOWING 1-7 OF 7 REFERENCES

Visualizing and Understanding Convolutional Networks

TLDR
A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.

Understanding Neural Networks Through Deep Visualization

TLDR
This work introduces several new regularization methods that combine to produce qualitatively clearer, more interpretable visualizations of convolutional neural networks.

Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks

TLDR
An algorithm is introduced that explicitly uncovers the multiple facets of each neuron by producing a synthetic visualization of each of the types of images that activate a neuron by separately synthesizing each type of image a neuron fires in response to.

ImageNet Large Scale Visual Recognition Challenge

TLDR
The creation of this benchmark dataset and the advances in object recognition that have been possible as a result are described, and the state-of-the-art computer vision accuracy with human accuracy is compared.

Blood Cell Images, version 6, 2018

  • URL https://www.kaggle. com/paultimothymooney/blood-cells
  • 2018

The Building Blocks of Interpretability

Feature Visualization

  • D. Silver
  • Computer Science
    Scientific Visualization
  • 1994