Talking about paper

1. Nature, Scientific Reports 4, Article number: 5552 (2014)

  "Imaging With Nature: Compressive Imaging Using a Multiply Scattering Medium" 

   The recent theory of compressive sensing leverages upon the structure of signals to acquire them with much fewer measurements than was previously thought necessary, and certainly well below the traditional Nyquist-Shannon sampling rate. However, most implementations developed to take advantage of this framework revolve around controlling the measurements with carefully engineered material or acquisition sequences. Instead, we use the natural randomness of wave propagation through multiply scattering media as an optimal and instantaneous compressive imaging mechanism. Waves reflected from an object are detected after propagation through a well-characterized complex medium. Each local measurement thus contains global information about the object, yielding a purely analog compressive sensing method. We experimentally demonstrate the effectiveness of the proposed approach for optical imaging by using a 300-micrometer thick layer of white paint as the compressive imaging device. Scattering media are thus promising candidates for designing efficient and compact compressive imagers.

Note: conventional random mask replaced by scattering media

2. Thesis "Supervised Sequence Labelling with Recurrent Neural Networks", http://www.cs.toronto.edu/~graves/preprint.pdf

    good material for sequence modeling.