Adepu Ravi Sankar

  • Citations Per Year
Learn More
Active learning algorithms automatically identify the salient and exemplar instances from large amounts of unlabeled data and thus reduce human annotation effort in inducing a classification model. More recently, Batch Mode Active Learning (BMAL) techniques have been proposed, where a batch of data samples is selected simultaneously from an unlabeled set.(More)
Data hiding in one of the easiest technique to authenticate and resolve the copyright issues of multimedia data. This paper proposes a new VLSI architecture for data hiding in grayscale images using neighbour mean image interpolation technique, as this mechanism will have a minimum computation complexity. In this VLSI based data hiding process the secret(More)
Energy-based deep learning models like Restricted Boltzmann Machines are increasingly used for real-world applications. However, all these models inherently depend on the Contrastive Divergence (CD) method for training and maximization of log likelihood of generating the given data distribution. CD, which internally uses Gibbs sampling, often does not(More)
In this paper, 2D integer wavelet transform based watermarking is carried out for the grayscale image with its VLSI architectural implementations. In the 2D integer wavelet transformation the lifting scheme is adopted and the watermarking operation is carried out in the LL2 frequency subbands. The entire watermark embedding process and extraction process(More)
Two major momentum-based techniques that have achieved tremendous success in optimization are Polyak’s heavy ball method and Nesterov’s accelerated gradient. A crucial step in all momentumbased methods is the choice of the momentum parameter m which is always suggested to be set to less than 1. Although the choice ofm < 1 is justified only under very strong(More)
  • 1