Search Results for author:
Found 10 papers, 1 papers with code
Memorization Capacity of Neural Networks with Conditional Computation
For Rectified Linear Unit (ReLU) networks without conditional computation, it is known that memorizing a collection of $n$ input-output relationships can be accomplished via a neural network with $O(\sqrt{n})$ neurons.
Class Based Thresholding in Early Exit Semantic Segmentation Networks
We propose Class Based Thresholding (CBT) to reduce the computational cost of early exit semantic segmentation models while preserving the mean intersection over union (mIoU) performance.
Pruning Early Exit Networks
Deep learning models that perform well often have high computational costs.
Federated Momentum Contrastive Clustering
We present federated momentum contrastive clustering (FedMCC), a learning framework that can not only extract discriminative representations over distributed local data but also perform data clustering.
Multiplication-Avoiding Variant of Power Iteration with Applications
In this paper, we introduce multiplication-avoiding power iteration (MAPI), which replaces the standard $\ell_2$-inner products that appear at the regular power iteration (RPI) with multiplication-free vector products which are Mercer-type kernel operations related with the $\ell_1$ norm.
Robust Principal Component Analysis Using a Novel Kernel Related with the L1-Norm
We consider a family of vector dot products that can be implemented using sign changes and addition operations only.
E$^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
Moreover, if there are no limitations on the training time budget, E$^2$CM can be combined with an existing early exit scheme to boost the latter's performance, achieving a better trade-off between computational cost and network accuracy.
Quantizing Multiple Sources to a Common Cluster Center: An Asymptotic Analysis
We consider quantizing an $Ld$-dimensional sample, which is obtained by concatenating $L$ vectors from datasets of $d$-dimensional vectors, to a $d$-dimensional cluster center.
Robust and Computationally-Efficient Anomaly Detection using Powers-of-Two Networks
We propose a technique to increase robustness and reduce computational complexity in a Convolutional Neural Network (CNN) based anomaly detector that utilizes the optical flow information of video data.
A Generalization of Principal Component Analysis
Conventional principal component analysis (PCA) finds a principal vector that maximizes the sum of second powers of principal components.
