Search Results for author:
Found 5 papers, 2 papers with code
Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations
Quantization based model compression serves as high performing and fast approach for inference that yields models which are highly compressed when compared to their full-precision floating point counterparts.
DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and $L_0$ Regularization
Modern neural network architectures typically have many millions of parameters and can be pruned significantly without substantial loss in effectiveness which demonstrates they are over-parameterized.
Ranked #46 on
Image Classification
on MNIST
SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features
These structural similarity features may be used with various algorithms however in this paper the focus and the second main contribution is on integrating these features with a revisited pooling layer DiffPool arXiv:1806. 08804 to propose a pooling layer referred to as SimPool.
Dynamic Time Warp Convolutional Networks
Where dealing with temporal sequences it is fair to assume that the same kind of deformations that motivated the development of the Dynamic Time Warp algorithm could be relevant also in the calculation of the dot product ("convolution") in a 1-D convolution layer.
Unsupervised Contextual Anomaly Detection using Joint Deep Variational Generative Models
A method for unsupervised contextual anomaly detection is proposed using a cross-linked pair of Variational Auto-Encoders for assigning a normality score to an observation.
Contextual Anomaly Detection
Unsupervised Contextual Anomaly Detection
