k-Winners-Take-All Ensemble Neural Network

1 code implementation • 4 Jan 2024 • Abien Fred Agarap, Arnulfo P. Azcarraga

We improve on these aforementioned ways for combining a group of neural networks by using a k-Winners-Take-All (kWTA) activation function, that acts as the combination method for the outputs of each sub-network in the ensemble.

Improving k-Means Clustering Performance with Disentangled Internal Representations

1 code implementation • 5 Jun 2020 • Abien Fred Agarap, Arnulfo P. Azcarraga

Deep clustering algorithms combine representation learning and clustering by jointly optimizing a clustering loss and a non-clustering loss.

Clustering Deep Clustering +2