Search Results for author: Somdeb Majumdar

Found 12 papers, 3 papers with code

Learning Spatial-Temporal Graphs for Active Speaker Detection

no code implementations2 Dec 2021 Sourya Roy, Kyle Min, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar

We address the problem of active speaker detection through a new framework, called SPELL, that learns long-range multimodal graphs to encode the inter-modal relationship between audio and visual data.

Audio-Visual Active Speaker Detection Node Classification

Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization

no code implementations14 Jun 2021 Santiago Miret, Vui Seng Chua, Mattias Marder, Mariano Phielipp, Nilesh Jain, Somdeb Majumdar

Our framework relies on Neuroevolution-Enhanced Multi-Objective Optimization (NEMO), a novel search method, to find Pareto optimal mixed-precision configurations for memory and bit-operations objectives.


On Local Aggregation in Heterophilic Graphs

no code implementations6 Jun 2021 Hesham Mostafa, Marcel Nassar, Somdeb Majumdar

We also show that homophily is a poor measure of the information in a node's local neighborhood and propose the Neighborhood Information Content(NIC) metric, which is a novel information-theoretic graph metric.

Node Classification

Dream and Search to Control: Latent Space Planning for Continuous Control

1 code implementation19 Oct 2020 Anurag Koul, Varun V. Kumar, Alan Fern, Somdeb Majumdar

Learning and planning with latent space dynamics has been shown to be useful for sample efficiency in model-based reinforcement learning (MBRL) for discrete and continuous control tasks.

Continuous Control Model-based Reinforcement Learning

Learning Intrinsic Symbolic Rewards in Reinforcement Learning

no code implementations8 Oct 2020 Hassam Sheikh, Shauharda Khadka, Santiago Miret, Somdeb Majumdar

We show that the discovered dense rewards are an effective signal for an RL policy to solve the benchmark tasks.

Safety Aware Reinforcement Learning (SARL)

no code implementations6 Oct 2020 Santiago Miret, Somdeb Majumdar, Carroll Wainwright

Since the safe agent effectively abstracts a task-independent notion of safety via its action probabilities, it can be ported to modulate multiple policies solving different tasks within the given environment without further training.

Collaborative Evolutionary Reinforcement Learning

1 code implementation2 May 2019 Shauharda Khadka, Somdeb Majumdar, Tarek Nassar, Zach Dwiel, Evren Tumer, Santiago Miret, Yinyin Liu, Kagan Tumer

Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks.

Continuous Control

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