SOURCE-LINKED INTELLIGENCE

Interpreting the predictions of neural network classification based on a Taylor Coefficient Analysis (TCA)

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

We introduce a rigid and comprehensive taxonomy and paradigm for characterizing the influence of the input feature space $X$ on the predictions $\hat{y}$ of a neural network (NN) used for event classification, based on a Taylor expansion of $\hat{y}$ in $X$. The complete process of introspection we refer to as Taylor Coefficient Analysis (TCA). Based on two simplistic example tasks, which can be easily understood and bencmarked, we illustrate the power of the TCA when it comes to revealing, what properties of $X$ have led to what value of $\hat{y}$, of a given NN model, building up intuition f

Read original source ↗ Open in workspace

recordType

paper

region

Global