Topological Gradient-based Competitive Learning

  title={Topological Gradient-based Competitive Learning},
  author={Pietro Barbiero and Gabriele Ciravegna and Vincenzo Randazzo and Giansalvo Cirrincione},
  journal={2021 International Joint Conference on Neural Networks (IJCNN)},
Topological learning is a wide research area aiming at uncovering the mutual spatial relationships between the elements of a set. Some of the most common and oldest approaches involve the use of unsupervised competitive neural networks. However, these methods are not based on gradient optimization which has been proven to provide striking results in feature extraction also in unsupervised learning. Unfortunately, by focusing mostly on algorithmic efficiency and accuracy, deep clustering… 
1 Citations

Figures and Tables from this paper


Nonstationary topological learning with bridges and convex polytopes: the G-EXIN neural network
The G-EXIN neural network, presented here, uses an anisotropic convex polytope, which, models the shape of the neuron neighborhood, and employs a novel kind of edge, called bridge, which carries information on the extent of the distribution time change.
Joint Unsupervised Learning of Deep Representations and Image Clusters
A recurrent framework for joint unsupervised learning of deep representations and image clusters by integrating two processes into a single model with a unified weighted triplet loss function and optimizing it end-to-end can obtain not only more powerful representations, but also more precise image clusters.
Deep Learning with Nonparametric Clustering
A deep belief network with nonparametric clustering that can learn features for clustering and infer model complexity in an unified framework and the experimental results show the advantage of the approach over competitive baselines.
Deep Adaptive Image Clustering
Deep Adaptive Clustering (DAC) is proposed that recasts the clustering problem into a binary pairwise-classification framework to judge whether pairs of images belong to the same clusters to overcome the main challenge, the ground-truth similarities are unknown in image clustering.
CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data
The proposed convolutional neural network to jointly solve clustering and representation learning in an iterative manner outperforms start-of-the-art clustering schemes in terms of accuracy and storage complexity on large-scale image sets containing millions of images.
Topology representing networks
Discovering Hierarchical Neural Archetype Sets
Experimental results on several benchmarks show that the proposed approach is competitive with traditional coreset discovery techniques, delivering results with higher accuracy, and showing a greater ability to generalize to unseen test data.
Competitive Hebbian Learning Rule Forms Perfectly Topology Preserving Maps
The problem of forming perfectly topology preserving maps of feature manifolds is studied. First, through introducing “masked Voronoi polyhedra” as a geometrical construct for determining
Learning Discrete Representations via Information Maximizing Self-Augmented Training
In IMSAT, data augmentation is used to impose the invari-ance on discrete representations and the predicted representations of augmented data points to be close to those of the original data points in an end-to-end fashion to maximize the information-theoretic dependency between data and their predicted discrete representations.
The GH-EXIN neural network for hierarchical clustering