Search Results for author:
Found 3 papers, 0 papers with code
Analysis of Interpolating Regression Models and the Double Descent Phenomenon
A regression model with more parameters than data points in the training data is overparametrized and has the capability to interpolate the training data.
Building Efficient CNNs Using Depthwise Convolutional Eigen-Filters (DeCEF)
During the analysis, we observe that the effective rank of the vectorized Conv2D filters decreases with respect to the increasing depth in the network, which then leads to the implementation of the Depthwise Convolutional Eigen-Filter (DeCEF) layer.
Learning Hierarchical Feature Space Using CLAss-specific Subspace Multiple Kernel -- Metric Learning for Classification
An extension to a hierarchical learning structure is also proposed to further improve the classification performance, where on each layer, the CLASMK is computed based on a selected "marginal" subset and feature vectors are constructed by concatenating the features from all previous layers.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
