Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Chenna Keshava, B.S.

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Survey on Optimization in IoT
    (Institute of Electrical and Electronics Engineers Inc., 2018) Chenna Keshava, B.S.; Srinivasan, C.K.
    This paper gives a brief overview of the existing literature on Optimization in Internet of Things (IoT), which is a very critical technology in the 21stcentury. A few of the papers deal with the evolution of IoT as a technology in the past 20 years, whereas a majority of the papers deal with the challenges faced in the communication, modelling and deployment of IoT applications, few of which use optimization and which are exploding in their numbers and the diversity of the type of devices. © 2018 IEEE.
  • No Thumbnail Available
    Item
    Role of Activation Functions and Order of Input Sequences in Question Answering
    (Springer, 2020) Chenna Keshava, B.S.; Sumukha, P.K.; Chandrasekaran, K.; Divakarla, D.
    This paper describes a solution for the Question Answering problem in Natural Language Processing using LSTMs. We perform an analysis on the effect of choice of activation functions in the final layer of LSTM cell on the accuracy. Facebook Research’s bAbI dataset is used for our experiments. We also propose an alternative solution, which exploits the language structure and order of words in the English language, i.e. reversing the order of paragraph will introduce many short-term dependencies between the textual data and the initial tokens of a question. This method improves the accuracy in more than half of the tasks by more than 30% over the current state of the art. Our contributions in this paper are improving the accuracy of most of the Q&A tasks by reversing the order of words in the query and the story sections. Also, we have provided a comparison of different activation functions and their respective accuracies with respect to all the 20 different NLP tasks. © 2020, Springer Nature Singapore Pte Ltd.