Topological Understanding of Neural Networks, a survey
This is an incremental survey that provides a topological perspective on neural network interpretability for researchers in machine learning.
This survey examines neural networks as black boxes, focusing on binary classification to understand their internal structure by reviewing activation functions, network architectures, and empirical data, with findings suggesting potential for verification on real datasets.
We look at the internal structure of neural networks which is usually treated as a black box. The easiest and the most comprehensible thing to do is to look at a binary classification and try to understand the approach a neural network takes. We review the significance of different activation functions, types of network architectures associated to them, and some empirical data. We find some interesting observations and a possibility to build upon the ideas to verify the process for real datasets. We suggest some possible experiments to look forward to in three different directions.