Search Results for author:
Found 6 papers, 2 papers with code
End-to-end deep meta modelling to calibrate and optimize energy consumption and comfort
Parameters are estimated by comparing the predictions of the metamodel with real data obtained from sensors using the CMA-ES algorithm, a derivative free optimization procedure.
One-Cycle Pruning: Pruning ConvNets Under a Tight Training Budget
Most of the time, sparsity is introduced using a three-stage pipeline: 1) train the model to convergence, 2) prune the model according to some criterion, 3) fine-tune the pruned model to recover performance.
End-to-end deep metamodeling to calibrate and optimize energy loads
Finally, the optimal settings to minimize the energy loads while maintaining a target thermal comfort and air quality are obtained using a multi-objective optimization procedure.
An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network
Neural networks usually involve a large number of parameters, which correspond to the weights of the network.
Improve Convolutional Neural Network Pruning by Maximizing Filter Variety
This technique ensures that the criteria of selection focuses on redundant filters, while retaining the rare ones, thus maximizing the variety of remaining filters.
Induced Feature Selection by Structured Pruning
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years.
