Ankit Vani
PhD student at Mila, Université de Montréal
E-mail: ![[firstname][dot][lastname]@umontreal.ca](email.png)
Github: ankitkv
I am a first year PhD student at Mila, Université de Montréal, under the supervision of Aaron Courville.
My goal is to improve our understanding of the principles underlying intelligence. My research seeks to find methods for reasoning about the world via unbounded computation using dynamic memory. Presently, I like to tackle tasks that force models to perform semantic understanding and reasoning with natural language. However, I'm also interested in the theory of deep learning and representation learning in general.
Education
- Ph.D., Machine Learning, Université de Montréal, ongoing
- M.S., Computer Science, New York University, 2017
- B.E., Computer Engineering, University of Pune, 2013
Research Interests
- Reasoning with natural language
- Memory-augmented neural networks
- Representation learning
Publications and Preprints
- Ankit Vani, Yacine Jernite, and David Sontag. Grounded Recurrent Neural Networks. arXiv:1705.08557 Preprint, May 2017. [pdf]
- Ramakrishna B Bairi, Ankit Vani, Pooja Ahuja, and Ganesh Ramakrishnan. Categorising videos using a personalised category catalogue. Proceedings of the 2nd ACM IKDD Conference on Data Sciences (CoDS 2015): March 2015. [pdf]
Research Reports
- Ankit Vani. Adversarial Discrete Sequence Generation. November 2017. [pdf] (advisor: Rob Fergus)
- Ankit Vani. Adversarial Objectives for Text Generation. December 2016. [pdf] (advisor: Kyunghyun Cho)
- Ankit Vani and Vighnesh Birodkar. Challenges with Variational Autoencoders for Text. December 2016. [pdf] (advisor: David Sontag)
- Ankit Vani and Srivas Venkatesh. Adjustable Text to Image Synthesis. December 2016. [pdf]
Other details on my Mila profile.
double l[]={2.237245047823e-312,3.01793166842199e-307};main(){(1[l]+=*l)?printf(l+1),1[l]=-*l,main():puts(l);}