no code implementations • 8 Nov 2020 • Alex Mathai, Shreya Khare, Srikanth Tamilselvam, Senthil Mani
On an average, we achieve an attack success rate of 65. 67% for SST and 36. 45% for IMDB across the three models showing an improvement of 49. 48% and 101% respectively.
no code implementations • 12 Oct 2020 • Raunak Sinha, Utkarsh Desai, Srikanth Tamilselvam, Senthil Mani
With the increase in the number of open repositories and discussion forums, the use of natural language for semantic code search has become increasingly common.
1 code implementation • 20 May 2020 • Naveen Panwar, Tarun Tater, Anush Sankaran, Senthil Mani
Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand.
1 code implementation • 31 Jan 2020 • Utkarsh Desai, Srikanth Tamilselvam, Jassimran Kaur, Senthil Mani, Shreya Khare
This emphasizes the need for a model agnostic test dataset, which consists of various corruptions that are natural to appear in the wild.
1 code implementation • 26 Nov 2019 • Ameya Prabhu, Riddhiman Dasgupta, Anush Sankaran, Srikanth Tamilselvam, Senthil Mani
Further, we predict the performance accuracy of the recommended architecture on the given unknown dataset, without the need for training the model.
no code implementations • 17 Nov 2019 • Senthil Mani, Anush Sankaran, Srikanth Tamilselvam, Akshay Sethi
Further, we conduct various experiments to demonstrate the effectiveness of systematic test case generation system for evaluating deep learning models.
no code implementations • 7 May 2019 • Srikanth Tamilselvam, Naveen Panwar, Shreya Khare, Rahul Aralikatte, Anush Sankaran, Senthil Mani
Deep learning is one of the fastest growing technologies in computer science with a plethora of applications.
no code implementations • 11 Nov 2018 • Tanmayee Narendra, Anush Sankaran, Deepak Vijaykeerthy, Senthil Mani
Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex.
no code implementations • 4 Nov 2018 • Shreya Khare, Rahul Aralikatte, Senthil Mani
Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • EMNLP 2018 • Rahul Aralikatte, Neelamadhav Gantayat, Naveen Panwar, Anush Sankaran, Senthil Mani
In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi.
no code implementations • 4 Jan 2018 • Senthil Mani, Anush Sankaran, Rahul Aralikatte
Using an attention mechanism enables the model to learn the context representation over a long word sequence, as in a bug report.
no code implementations • 1 Jan 2018 • Rahul Aralikatte, Neelamadhav Gantayat, Naveen Panwar, Anush Sankaran, Senthil Mani
In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi.
no code implementations • 9 Nov 2017 • Akshay Sethi, Anush Sankaran, Naveen Panwar, Shreya Khare, Senthil Mani
To address these challenges, we propose a novel extensible approach, DLPaper2Code, to extract and understand deep learning design flow diagrams and tables available in a research paper and convert them to an abstract computational graph.
no code implementations • 2 Nov 2017 • Senthil Mani, Neelamadhav Gantayat, Rahul Aralikatte, Monika Gupta, Sampath Dechu, Anush Sankaran, Shreya Khare, Barry Mitchell, Hemamalini Subramanian, Hema Venkatarangan
Question answering is one of the primary challenges of natural language understanding.
no code implementations • 16 Aug 2017 • Naveen Panwar, Shreya Khare, Neelamadhav Gantayat, Rahul Aralikatte, Senthil Mani, Anush Sankaran
Cross-modal data retrieval has been the basis of various creative tasks performed by Artificial Intelligence (AI).
no code implementations • 16 Aug 2017 • Rahul Aralikatte, Giriprasad Sridhara, Neelamadhav Gantayat, Senthil Mani
Further, we developed three systems; two of which were based on traditional machine learning and one on deep learning to automatically identify reviews whose rating did not match with the opinion expressed in the review.