Overview
- Deep learning(DL) is an area of machine learning that deals with artificial neural networks, which are algorithms inspired by the structure and function of the brain.
- Autoencoder(AE): An Autoencoder is a type of artificial neural network that has bottleneck architecture that turns a high-dimensional input into a latent low-dimensional code (encoder), and then performs a reconstruction of the input with this latent code (the decoder).
- Denoising Autoencoder(DAE): is a modification of the autoencoder. Denoising autoencoders corrupt the input data, adding noise to the input image, and then try to reconstruct the original image from the noisy image.
Abstract:
|
Approach:
|
Hyperparameters: Result:
The results showed 0.0117 loss for MNIST dataset after 10 epochs.
Concepts used:
Convolution in Image
Denoising Autoencoder
GitHub Repository
Tools and Libraries used:
Team members:
|
Team Mentors:
|