Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Reimagining the world in 2050
Published:
In 1990, when my father was turning 20 he had several aspirations about how life would change after 30 years. He envisioned a better quality of life for his family, technology-oriented world, better purchasing parity and growth-oriented employment opportunities. Needless to say, many of his aspirations and wishes turned out to be true. Similarly in my 20’s, I cannot help wonder how aspects of life would be different in 2050
Education Coronafied: How the pandemic is changing student lives
Published:
Just like every other demographic, the student community has been affected in several ways due to the coronavirus pandemic. Even though young people are least vulnerable to the virus, the fallout from the pandemic including recession, school closures have brought permanent changes to certain aspects of everyday student life. Some of these aspects include
My Udacity Pytorch Scholarship Challenge Experience
Published:
Udacity sponsored a Challenge Program to select students for its Deep Learning with Pytorch Nanodegree.The following article enumerates my experience during the Challenge Program and tips for future students who might qualify for this challenge. The Challenge was announced at the first ever Pytorch Developer Conference by Udacity in collaboration with the Facebook.The aim was to select 10,000 students initially offer them an initial course material along with community support on Slack.The top 300 students would then be selected for the Deep Learning Nanodegree sponsored by Facebook.The Selection process involved filling out a standard questionnaire on the basis of which a global pool of 10k students were selected.
portfolio
publications
Gender Classification using Facial Embeddings: A Novel Approach
Published in ELseveir Procedia Computer Science Journal, 2009
Image Processing for Human recognition involves using bio-metric traits such as Face, Iris, Voice and other physical traits to uniquely identify human faces. With the increase in Image Data on the Internet, there is a huge demand for Artificial Intelli-gence(AI) algorithms that can perform classification tasks like Race and Gender Classification. The advent of Deep Learning Techniques like Convolutional Networks has led to a rapid ascent in accuracy in various image classification tasks. Through this paper, a novel method to predict Gender of a person by applying various Machine Learning Classification Techniques on Facial Em-beddings has been proposed. The facial embeddings are found by passing through a Pretrained Inception Network. The maximum accuracy obtained by the proposed work to classify gender is 97%.
Recommended citation: Avinash Swaminathan , Mridul Chaba, Deepak Kumar Sharma,and Yogesh Chaba. Gender Classification using Facial Embeddings: A Novel Approach. Procedia Computer Science , 167:2634 – 2642, 2020. International Conference on Computational Intelligence and Data Science. https://www.sciencedirect.com/science/article/pii/S1877050920308085
Keyphrase generation for scientific articles using gans (student abstract)
Published in AAAI Conference on Artificial Intelligence 2020, 2022
In this paper, we present a keyphrase generation approach using conditional Generative Adversarial Networks (GAN). In our GAN model, the generator outputs a sequence of keyphrases based on the title and abstract of a scientific article. The discriminator learns to distinguish between machine-generated and human-curated keyphrases. We evaluate this approach on standard benchmark datasets. Our model achieves state-of-the-art performance in generation of abstractive keyphrases and is also comparable to the best performing extractive techniques. We also demonstrate that our method generates more diverse keyphrases and make our implementation publicly available
Recommended citation: Swaminathan, A., Gupta, R. K., Zhang, H., Mahata, D., Gosangi, R., & Shah, R. R. (2020). Keyphrase Generation for Scientific Articles Using GANs (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence , 34(10), 13931-13932. https://doi.org/10.1609/aaai.v34i10.7238 https://ojs.aaai.org/index.php/AAAI/article/view/7238
A Preliminary Exploration of GANs for Keyphrase Generation
Published in 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022
We introduce a new keyphrase generation approach using Generative Adversarial Networks (GANs). For a given document, the generator produces a sequence of keyphrases, and the discriminator distinguishes between human-curated and machinegenerated keyphrases. We evaluated this approach on standard benchmark datasets. We observed that our model achieves state-of-theart performance in the generation of abstractive keyphrases and is comparable to the best performing extractive techniques. Although we achieve promising results using GANs, they are not significantly better than the stateof-the-art generative models. To our knowledge, this is one of the first works that use GANs for keyphrase generation. We present a detailed analysis of our observations and expect that these findings would help other researchers to further study the use of GANs for the task of keyphrase generation.
Recommended citation: Avinash Swaminathan, Haimin Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah, and Amanda Stent.A preliminary exploration of GANs for keyphrase generation. In Proceedings of the 2020 Conference onEmpirical Methods in Natural Language Processing (EMNLP), pages 8021–8030, Online, November 2020. Associationfor Computational Linguistics. https://www.aclweb.org/anthology/2020.emnlp-main.645.pdf
Two-Step Classification using Recasted Data for Low Resource Settings
Published in 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2022
An NLP model’s ability to reason should be independent of language. Previous works utilize Natural Language Inference (NLI) to understand the reasoning ability of models, mostly focusing on high resource languages like English. To address scarcity of data in low-resource languages such as Hindi, we use data recasting to create NLI datasets for four existing text classification datasets. Through experiments, we show that our recasted dataset is devoid of statistical irregularities and spurious patterns. We further study the consistency in predictions of the textual entailment models and propose a consistency regulariser to remove pairwise-inconsistencies in predictions. We propose a novel two-step classification method which uses textual-entailment predictions for classification task. We further improve the performance by using a joint-objective for classification and textual entailment. We therefore highlight the benefits of data recasting and improvements on classification performance using our approach with supporting experimental results.
Recommended citation: Shagun Uppal , Vivek Gupta ,Avinash Swaminathan, Haimin Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah, and Amanda Stent.Two-step classification using recasted data for low resource settings. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing , pages 706–719, Suzhou, China, December 2020. Association for Computational Linguistics. https://www.aclweb.org/anthology/2020.aacl-main.71.pdf
talks
Top 10 mistakes not to make during IITJEE Preparation #IITJEE #JEEAdvanced
Published:
I secured rank 6738 in JEE Advanced 2020. Here are my top 10 mistakes which students should not make during their JEE Advanced Preparation. I hope you guys find it helpful. Wish you guys all the best for JEE Advanced.
Youtube Webinar on FaceNet: A Unified Embedding for Face Recognition and Clustering
Published:
I recently conducted a Webinar on Facial Recognition and Clustering using Facial Embeddings.We discussed what an Embedding Matrix was and how it helps us in the low-level representation of the characteristics of any matrix .We also discussed how Haar Cascades worked. A thorough discussion of the Facenet paper was also carried out.
A Preliminary Exploration of GANs for keyphrase generation - EMNLP 2020 short paper
Published:
This is a presentation of our short Paper by “ A Preliminary Exploration of GANs for keyphrase generation “ presented at EMNLP 2020. The authors of this paper are : Avinash Swaminathan, Raymond(Haimin) Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah, Amanda Stent. This a joint collaboration between Bloomberg, NYC and MIDAS, IIITD. Our work was also presented at AAAI 2020. The slides were recorded over SlidesLive.
Pytorch Tutorial - Chapter 1: Tensors
Published:
Over a few series of weeks, I will be releasing a series of videos teaching various Pytorch concepts. Today we will be talking all about torch Tensors. The table of contents are as follows