73 citations · 168 across the 11 of their papers we have counts for
7 papers · 1 filter
Learning in Convolutional Neural Networks Accelerated by Transfer Entropy
Adrian Moldovan, Angel Caţaron, Răzvan Andonie
Recently, there is a growing interest in applying Transfer Entropy (TE) in quantifying the effective connectivity between artificial neurons. In a feedforward network, the TE can b…
Information Plane Analysis Visualization in Deep Learning via Transfer Entropy
Adrian Moldovan, Angel Cataron, Razvan Andonie
In a feedforward network, Transfer Entropy (TE) can be used to measure the influence that one layer has on another by quantifying the information transfer between them during train…
Pruning Convolutional Filters via Reinforcement Learning with Entropy Minimization
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 embedd…
Learning in Feedforward Neural Networks Accelerated by Transfer Entropy
Adrian Moldovan, Angel Caţaron, Răzvan Andonie
Current neural networks architectures are many times harder to train because of the increasing size and complexity of the used datasets. Our objective is to design more efficient t…
Semiotic Aggregation in Deep Learning
Bogdan Musat, Razvan Andonie
Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the…
Weighted Random Search for Hyperparameter Optimization
Adrian-Catalin Florea, Razvan Andonie
We introduce an improved version of Random Search (RS), used here for hyperparameter optimization of machine learning algorithms. Unlike the standard RS, which generates for each t…
Weighted Random Search for CNN Hyperparameter Optimization
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). While the training par…