Skip to content

Ranjan Kumar

Menu
  • About Me
  • My Papers
Menu

Explainable Neural Networks

Posted on July 3, 2021July 10, 2021 by Ranjan Kumar
  • Explainable Neural Networks: Recent Advancements, Part 1
  • Explainable Neural Networks: Recent Advancements, Part 2
  • Explainable Neural Networks: Recent Advancements, Part 3
  • Network In Network by Min Lin 2013

Gradient Based Approaches

Visualizing Gradients (2014)

In the paper “Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps“ Karen Simonyan et. al. proposed two visualisation techniques, based on computing the gradient of the class score with respect to the input image.

  1. The first technique generates an image, which maximises the class score, visualising the notion of the class, captured by a ConvNet.
  2. The second technique computes a class saliency map, specific to a given image and class.

Search

Recent Posts

  • Leadership Pointers
  • Tips & Tricks – Software Development
  • Design Principles
  • Clustering
  • Search Engine
  • Medical Imaging
  • Cloud Computing Concepts
  • Distributed Deep Learning
  • Multimodal Deep Learning
  • Deep Reinforcement Learning

Categories

  • AI & ML
  • Cloud Computing
  • Computer Vision
  • Deep Learning
  • Deep Reinforcement Learning
  • Explainable AI
  • Medical Imaging
  • Others
  • Reinforcement Learning
  • Software Development
  • Uncategorized