Search Results for author:
Found 6 papers, 4 papers with code
Detach-ROCKET: Sequential feature selection for time series classification with random convolutional kernels
When applied to the largest binary UCR dataset, Detach-ROCKET is able to improve test accuracy by $0. 6\%$ while reducing the number of features by $98. 9\%$.
Emergent representations in networks trained with the Forward-Forward algorithm
The Backpropagation algorithm has often been criticised for its lack of biological realism.
CARSO: Blending Adversarial Training and Purification Improves Adversarial Robustness
In this work, we propose a novel adversarial defence mechanism for image classification - CARSO - blending the paradigms of adversarial training and adversarial purification in a mutually-beneficial, robustness-enhancing way.
Hierarchical nucleation in deep neural networks
This process leaves a footprint in the probability density of the output layer where the topography of the peaks allows reconstructing the semantic relationships of the categories.
Intrinsic dimension of data representations in deep neural networks
We find that, in a trained network, the ID is orders of magnitude smaller than the number of units in each layer.
Observing the Population Dynamics in GE by means of the Intrinsic Dimension
We explore the use of Intrinsic Dimension (ID) for gaining insights in how populations evolve in Evolutionary Algorithms.
