Supervised Dimensionality Reduction and Image Classification Utilizing Convolutional Autoencoders

by   Ioannis A. Nellas, et al.

The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a Convolutional Autoencoder for dimensionality reduction and a classifier composed by a Fully Connected Network, are combined to simultaneously produce supervised dimensionality reduction and predictions. It turned out that this methodology can also be greatly beneficial in enforcing explainability of deep learning architectures. Additionally, the resulting Latent Space, optimized for the classification task, can be utilized to improve traditional, interpretable classification algorithms. The experimental results, showed that the proposed methodology achieved competitive results against the state of the art deep learning methods, while being much more efficient in terms of parameter count. Finally, it was empirically justified that the proposed methodology introduces advanced explainability regarding, not only the data structure through the produced latent space, but also about the classification behaviour.


page 14

page 15

page 16

page 18


Dimensionality Reduction by Local Discriminative Gaussians

We present local discriminative Gaussian (LDG) dimensionality reduction,...

Unexplainable Explanations: Towards Interpreting tSNE and UMAP Embeddings

It has become standard to explain neural network latent spaces with attr...

Dimensionality Reduction in Deep Learning via Kronecker Multi-layer Architectures

Deep learning using neural networks is an effective technique for genera...

Variational voxelwise rs-fMRI representation learning: Evaluation of sex, age, and neuropsychiatric signatures

We propose to apply non-linear representation learning to voxelwise rs-f...

A Deep Embedded Refined Clustering Approach for Breast Cancer Distinction based on DNA Methylation

Epigenetic alterations have an important role in the development of seve...

Autoencoding with a Learning Classifier System: Initial Results

Autoencoders enable data dimensionality reduction and a key component of...

Multi-Sensor Fusion via Reduction of Dimensionality

Large high-dimensional datasets are becoming more and more popular in an...

Please sign up or login with your details

Forgot password? Click here to reset