Dimension reduction for image clustering using convolutional autoencoder

Nov 3, 2018


About workshop

Kostiantyn Isaienkov on the workshop we will describe the solution for the task of the dimension reduction of the image dataset for further clustering using convolutional autoencoder. The program includes the following steps:
1. Building and training autoencoder model (python3, keras).
2. Dimension reduction of real image dataset via autoencoder model.
3. Clustering of image dataset.
4. Comparing precision of convolutional neural network trained on original dataset with another feed-forward neural network trained on compressed dataset.
5. Image dataset clustering (python3, kmeans).
Most clustering algorithms require the linear dimension of the dataset. In the case of images, we are dealing with a 3-dimension matrix (height, width, 3 rgb values). The convolutional autoconcoder allows to reduce the image dataset to 1-ddimensional form. Correct approach for selection of the size of the bottleneck (the dimension of the compressed data) allows to decrease loss of precision.

Linux OS and Docker must be installed on the laptops for the workshop. We will send you all the needed info for the workshop 3 days before the conference. If you have any questions, please, join the DS Community in Telegram  https://t.me/OctopusAI