Training Autoencoders in Sparse Domain


  • Biswarup Bhattacharya University of Southern California
  • Arna Ghosh McGill University
  • Somnath Basu Roy Chowdhury Indian Institute of Technology Kharagpur


Autoencoders, Neural networks, Fast Fourier Transform, Discrete Cosine Transform


Autoencoders (AE) are essential in learning representation of large data (like images) for dimensionality reduction. Images are converted to sparse domain using transforms like Fast Fourier Transform (FFT) or Discrete Cosine Transform (DCT) where information that requires encoding is minimal. By optimally selecting the feature-rich frequencies, we are able to learn the latent vectors more robustly. We successfully show enhanced performance of autoencoders in sparse domain for images.




How to Cite

Bhattacharya, B., Ghosh, A., & Basu Roy Chowdhury, S. (2018). Training Autoencoders in Sparse Domain. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from