no code implementations • 3 Apr 2024 • Adrian Moldovan, Angel Caţaron, Răzvan Andonie
According to our experiments on CNN classifiers, to achieve a reasonable computational overhead--accuracy trade-off, it is efficient to consider only the inter-neural information transfer of a random subset of the neuron pairs from the last two fully connected layers.
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 • 29 Apr 2021 • Adrian Moldovan, Angel Caţaron, Răzvan Andonie
Our contribution is an information-theoretical method for analyzing information transfer between the nodes of feedforward neural networks.