STAD is a graph-based method that approximates high-dimensional data structure by extending a minimum spanning tree through edge addition to maximize distance correlation.
Understanding Deep Neural Networks Using Topological Data Analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Deep neural networks (DNN) are black box algorithms. They are trained using a gradient descent back propagation technique which trains weights in each layer for the sole goal of minimizing training error. Hence, the resulting weights cannot be directly explained. Using Topological Data Analysis (TDA) we can get an insight on how the neural network is thinking, specifically by analyzing the activation values of validation images as they pass through each layer.
fields
cs.GR 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving the Projection of Global Structures in Data through Spanning Trees
STAD is a graph-based method that approximates high-dimensional data structure by extending a minimum spanning tree through edge addition to maximize distance correlation.