Search Results for author:
Found 4 papers, 0 papers with code
Experimental Observations of the Topology of Convolutional Neural Network Activations
Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures.
The SVD of Convolutional Weights: A CNN Interpretability Framework
Fully connected layers can be studied by decomposing their weight matrices using a singular value decomposition, in effect studying the correlations between the rows in each matrix to discover the dynamics of the map.
Hypergraph Models of Biological Networks to Identify Genes Critical to Pathogenic Viral Response
Results: We compiled a novel data set of transcriptional host response to pathogenic viral infections and formulated relationships between genes as a hypergraph where hyperedges represent significantly perturbed genes, and vertices represent individual biological samples with specific experimental conditions.
Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers
First, the success rate of backdoor poisoning attacks varies widely, depending on several factors, including model architecture, trigger pattern and regularization technique.
