Advanced Project References

Evolutionary Visual Analysis of Deep Neural Networks

Key Points in Each Section

1. Introduction

A visual analytics framework for network evolution monitoring needs to possess the following three important capabilities:

  • Monitor neural network evolution
  • Rigorous quantitative evaluation
  • Expand theoretical insights

2. Methodology

2.1 Discriminability Metric

In deep learning, the loss function is a metric for the class-wise discriminability evaluation of the neurons.

How to evaluate those neurons in the inner layers? Due to the lack of ground truth for specific classes or visual concepts, it is challenging to quantitvatively evaluate them.

*** HOW TO COMPUTE THE DISCRIMINABILITY

References

What is a Loss Function?

Deep Learning: Overview of Neurons and Activation Functions