Search Results for author: G. Srinivasaraghavan

Found 7 papers, 0 papers with code

AI based approach to Trailer Generation for Online Educational Courses

no code implementations10 Jan 2023 Prakhar Mishra, Chaitali Diwan, Srinath Srinivasa, G. Srinivasaraghavan

It also helps to generate curiosity and interest among the learners and encourages them to pursue a course.

Video Editing

Why Settle for Just One? Extending EL++ Ontology Embeddings with Many-to-Many Relationships

no code implementations20 Oct 2021 Biswesh Mohapatra, Sumit Bhatia, Raghava Mutharaju, G. Srinivasaraghavan

However, most of the existing KG embeddings only consider the network structure of the graph and ignore the semantics and the characteristics of the underlying ontology that provides crucial information about relationships between entities in the KG.

Link Prediction Question Answering

Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning

no code implementations23 Mar 2021 Sonal Garg, Sumanth Prabhu, Hemant Misra, G. Srinivasaraghavan

Given that the agents as well as the customers can have varying levels of literacy, the overall quality of responses provided by the agents tend to be poor if they are not predefined.

Natural Language Inference Paraphrase Generation +4

Learning a Deep Reinforcement Learning Policy Over the Latent Space of a Pre-trained GAN for Semantic Age Manipulation

no code implementations2 Nov 2020 Kumar Shubham, Gopalakrishnan Venkatesh, Reijul Sachdev, Akshi, Dinesh Babu Jayagopi, G. Srinivasaraghavan

In our work, we have formulated a Markov Decision Process (MDP) over the latent space of a pre-trained GAN model to learn a conditional policy for semantic manipulation along specific attributes under defined identity bounds.

Learning agents with prioritization and parameter noise in continuous state and action space

no code implementations ICLR 2019 Rajesh Devaraddi, G. Srinivasaraghavan

Deep Q-learning networks (DQN) and Deep Deterministic Policy Gradient (DDPG) are two such methods that have shown state-of-the-art results in recent times.

Autonomous Vehicles Q-Learning +2

Human Trajectory Prediction using Spatially aware Deep Attention Models

no code implementations26 May 2017 Daksh Varshneya, G. Srinivasaraghavan

All these approaches have been limited by problems like inefficient features in the case of hand crafted features, large error propagation across the predicted trajectory and no information of static artefacts around the dynamic moving objects.

Deep Attention Trajectory Prediction

Phoenix: A Self-Optimizing Chess Engine

no code implementations30 Mar 2016 Rahul Aralikatte, G. Srinivasaraghavan

With the advent of deep learning, chess playing agents can surpass human ability with relative ease.

Game of Chess

Cannot find the paper you are looking for? You can Submit a new open access paper.