mathblender17 / cae_autoencoders_cifar_10

CAE_autoencoders_CIFAR_10

Here I have implemented CAE - Convolution AutoEncoder for the task of feature extraction on the CIFAR-10 Dataset using keras and TenserFlow.

CIFAR-10:

• Contains 60,000 images of 32x32 pixels belonging to 10 mutually exclusive classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck.
• Includes 50,000 training images and 10,000 testing images.
• https://paperswithcode.com/dataset/cifar-10

Convolutional Autoencoder (CAE):

A Convolutional Autoencoder (CAE) is a type of artificial neural network that learns to compress and reconstruct input data (often images) in a compressed, low-dimensional representation.

• CAEs are effective for feature extraction, as the latent space captures important features of the input data in a low-dimensional form.

• They can be used for dimensionality reduction, data compression, and anomaly detection.

• Compared to regular autoencoders, they are specifically designed for images and leverage the spatial structure of the data.

  Results