research
∙
07/03/2023
Learning to Communicate using Contrastive Learning
Communication is a powerful tool for coordination in multi-agent RL. But...
share
research
∙
03/07/2022
Reinforcement Learning for Location-Aware Scheduling
Recent techniques in dynamical scheduling and resource management have f...
research
∙
03/07/2022
Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning
For communication to happen successfully, a common language is required ...
research
∙
03/06/2022
Hierarchically Structured Scheduling and Execution of Tasks in a Multi-Agent Environment
In a warehouse environment, tasks appear dynamically. Consequently, a ta...
research
∙
06/17/2021
On the Dark Side of Calibration for Modern Neural Networks
Modern neural networks are highly uncalibrated. It poses a significant c...
research
∙
04/30/2018
How Robust are Deep Neural Networks?
Convolutional and Recurrent, deep neural networks have been successful i...
research
∙
11/14/2017
Conditional Autoencoders with Adversarial Information Factorization
Generative models, such as variational auto-encoders (VAE) and generativ...
research
∙
11/08/2017
LatentPoison - Adversarial Attacks On The Latent Space
Robustness and security of machine learning (ML) systems are intertwined...
research
∙
10/25/2017
GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks
The Fisher information metric is an important foundation of information ...
research
∙
10/19/2017
Generative Adversarial Networks: An Overview
Generative adversarial networks (GANs) provide a way to learn deep repre...
research
∙
10/11/2017
StackSeq2Seq: Dual Encoder Seq2Seq Recurrent Networks
A widely studied non-deterministic polynomial time (NP) hard problem lie...
research
∙
10/11/2017
Sequence stacking using dual encoder Seq2Seq recurrent networks
A widely studied non-polynomial (NP) hard problem lies in finding a rout...
research
∙
09/07/2017
Approximating meta-heuristics with homotopic recurrent neural networks
Much combinatorial optimisation problems constitute a non-polynomial (NP...
research
∙
08/18/2017
Pillar Networks++: Distributed non-parametric deep and wide networks
In recent work, it was shown that combining multi-kernel based support v...
research
∙
07/21/2017
Multi-kernel learning of deep convolutional features for action recognition
Image understanding using deep convolutional network has reached human-l...
research
∙
05/20/2017
Bayesian Belief Updating of Spatiotemporal Seizure Dynamics
Epileptic seizure activity shows complicated dynamics in both space and ...
research
∙
05/17/2017