SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries
Current Deep Network (DN) visualization and interpretability methods rely heavily on data space visualizations such as scoring which dimensions of the data are responsible for their associated prediction or generating new data features or samples that best match a given DN unit or representation. In this paper, we go one step further by developing the first provably exact method for computing the geometry of a DN's mapping - including its decision boundary - over a specified region of the data space. By leveraging the theory of Continuous Piece-Wise Linear (CPWL) spline DNs, SplineCam exactly computes a DNs geometry without resorting to approximations such as sampling or architecture simplification. SplineCam applies to any DN architecture based on CPWL nonlinearities, including (leaky-)ReLU, absolute value, maxout, and max-pooling and can also be applied to regression DNs such as implicit neural representations. Beyond decision boundary visualization and characterization, SplineCam enables one to compare architectures, measure generalizability and sample from the decision boundary on or off the manifold. Project Website: bit.ly/splinecam.
Code (1)
Similar Papers 제목 키워드 기반
On the Decision Boundaries of Deep Neural Networks: A Tropical Geometry Perspective
This work tackles the problem of characterizing and understanding the decision boundaries of neural networks with piece-wise linear non-linearity activations. We use tropical geometry, a new development in the area of al…
Network PruningSwitching-Geometry Analysis of Deflated Q-Value Iteration
This paper develops a joint spectral radius (JSR) framework for analyzing rank-one deflated Q-value iteration (Q-VI) in discounted Markov decision process control. Focusing on an all-ones residual correction, we interpre…
Point Location and Active Learning: Learning Halfspaces Almost Optimally
Given a finite set $X \subset \mathbb{R}^d$ and a binary linear classifier $c: \mathbb{R}^d \to \{0,1\}$, how many queries of the form $c(x)$ are required to learn the label of every point in $X$? Known as \textit{point …
Active LearningPositionThe Decision Geometry of Covariance Estimation for the Global Minimum-Variance Portfolio under Heavy Tails
The global minimum-variance portfolio (GMVP) is the canonical decision built from an estimated covariance matrix, yet covariance estimators are universally evaluated by matrix-norm loss, which is not the object the decis…
Geometry- and Accuracy-Preserving Random Forest Proximities
Random forests are considered one of the best out-of-the-box classification and regression algorithms due to their high level of predictive performance with relatively little tuning. Pairwise proximities can be computed …
Data VisualizationImputationOutlier Detectionregression