no code implementations • 1 Apr 2024 • Adrian Moldovan, Angel Cataron, Razvan Andonie
Information Plane analysis is a visualization technique used to understand the trade-off between compression and information preservation in the context of the Information Bottleneck method by plotting the amount of information in the input data against the compressed representation.
no code implementations • 8 Dec 2023 • Bogdan Musat, Razvan Andonie
We propose a novel method to improve MI computation for CNN pruning, using the spatial aura entropy.
no code implementations • 8 Dec 2023 • Bogdan Musat, Razvan Andonie
Structural pruning has become an integral part of neural network optimization, used to achieve architectural configurations which can be deployed and run more efficiently on embedded devices.
no code implementations • 22 Apr 2021 • Bogdan Musat, Razvan Andonie
To the extent of our knowledge, this is the first application of computational semiotics in the analysis and interpretation of deep neural networks.
1 code implementation • 3 Apr 2020 • Adrian-Catalin Florea, Razvan Andonie
We introduce an improved version of Random Search (RS), used here for hyperparameter optimization of machine learning algorithms.
1 code implementation • 30 Mar 2020 • Razvan Andonie, Adrian-Catalin Florea
Nearly all model algorithms used in machine learning use two different sets of parameters: the training parameters and the meta-parameters (hyperparameters).
2 code implementations • 3 Apr 2017 • Joseph Lemley, Filip Jagodzinski, Razvan Andonie
We present the first algorithm for finding holes in high dimensional data that runs in polynomial time with respect to the number of dimensions.
Computational Geometry Data Analysis, Statistics and Probability