: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
This paper develops a new class of algorithms for signal recovery in the distributed compressive sensing (DCS) framework. DCS exploits both intra-signal and inter-signal correlati...
Stephen R. Schnelle, Jason N. Laska, Chinmay Hegde...
- In this paper a Discrete Wavelet Transform based blind watermarking algorithm is proposed for embedding a grayscale watermark into a grayscale image. A new approach of choosing t...
Shikha Tripathi, Sai Krishnan Ramachandran, Vijay ...
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true d...
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...