no code implementations • 3 Jul 2023 • Yat Long Lo, Biswa Sengupta, Jakob Foerster, Michael Noukhovitch
By examining the relationship between messages sent and received, we propose to learn to communicate using contrastive learning to maximize the mutual information between messages of a given trajectory.
no code implementations • 15 Mar 2022 • Guo Ye, Han Liu, Biswa Sengupta
In multi-agent collaboration problems with communication, an agent's ability to encode their intention and interpret other agents' strategies is critical for planning their future actions.
no code implementations • 14 Mar 2022 • Qinjie Lin, Han Liu, Biswa Sengupta
Our results also demonstrate the advantage of the switch transformer model for absorbing expert knowledge and the importance of value distribution in evaluating the trajectory.
no code implementations • 14 Mar 2022 • Tim Tsz-Kit Lau, Biswa Sengupta
We study two state-of-the-art solutions to the multi-agent pickup and delivery (MAPD) problem based on different principles -- multi-agent path-finding (MAPF) and multi-agent reinforcement learning (MARL).
Multi-Agent Path Finding Multi-agent Reinforcement Learning +2
no code implementations • 7 Mar 2022 • Stelios Stavroulakis, Biswa Sengupta
Recent techniques in dynamical scheduling and resource management have found applications in warehouse environments due to their ability to organize and prioritize tasks in a higher temporal resolution.
no code implementations • 7 Mar 2022 • Yat Long Lo, Biswa Sengupta
For communication to happen successfully, a common language is required between agents to understand information communicated by one another.
no code implementations • 6 Mar 2022 • Diogo S. Carvalho, Biswa Sengupta
In this work, we set ourselves on a problem that presents itself with a hierarchical structure: the task-scheduling, by a centralised agent, in a dynamic warehouse multi-agent environment and the execution of one such schedule, by decentralised agents with only partial observability thereof.
no code implementations • 17 Jun 2021 • Aditya Singh, Alessandro Bay, Biswa Sengupta, Andrea Mirabile
We find that many calibration approaches with the likes of label smoothing, mixup etc.
no code implementations • 22 Jan 2020 • Lancelot Da Costa, Thomas Parr, Biswa Sengupta, Karl Friston
We then show that these neuronal dynamics approximate natural gradient descent, a well-known optimisation algorithm from information geometry that follows the steepest descent of the objective in information space.
no code implementations • 30 Apr 2018 • Biswa Sengupta, Karl J. Friston
In this paper, we evaluate the robustness of three recurrent neural networks to tiny perturbations, on three widely used datasets, to argue that high accuracy does not always mean a stable and a robust (to bounded perturbations, adversarial attacks, etc.)
no code implementations • ICLR 2018 • Biswa Sengupta, Yu Qian
In recent work, it was shown that combining multi-kernel based support vector machines (SVMs) can lead to near state-of-the-art performance on an action recognition dataset (HMDB-51 dataset).
no code implementations • ICLR 2018 • Antonia Creswell, Biswa Sengupta, Anil A. Bharath
Robustness and security of machine learning (ML) systems are intertwined, wherein a non-robust ML system (classifiers, regressors, etc.)
1 code implementation • ICLR 2019 • Antonia Creswell, Yumnah Mohamied, Biswa Sengupta, Anil A. Bharath
We propose a novel generative model architecture designed to learn representations for images that factor out a single attribute from the rest of the representation.
1 code implementation • 8 Nov 2017 • Antonia Creswell, Anil A. Bharath, Biswa Sengupta
Robustness and security of machine learning (ML) systems are intertwined, wherein a non-robust ML system (classifiers, regressors, etc.)
no code implementations • ICLR 2018 • Alessandro Bay, Biswa Sengupta
The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution.
2 code implementations • 19 Oct 2017 • Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, Anil A. Bharath
Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data.
no code implementations • 11 Oct 2017 • Alessandro Bay, Biswa Sengupta
A widely studied non-deterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph.
no code implementations • 7 Sep 2017 • Alessandro Bay, Biswa Sengupta
We show the viability of recurrent neural network solutions on a graph that has over 300 nodes and argue that a sequence-to-sequence network rather than other recurrent networks has improved approximation quality.
no code implementations • 18 Aug 2017 • Biswa Sengupta, Yu Qian
In recent work, it was shown that combining multi-kernel based support vector machines (SVMs) can lead to near state-of-the-art performance on an action recognition dataset (HMDB-51 dataset).
no code implementations • 21 Jul 2017 • Biswa Sengupta, Yu Qian
Image understanding using deep convolutional network has reached human-level performance, yet a closely related problem of video understanding especially, action recognition has not reached the requisite level of maturity.
no code implementations • 20 May 2017 • Gerald K Cooray, Richard Rosch, Torsten Baldeweg, Louis Lemieux, Karl Friston, Biswa Sengupta
Epileptic seizure activity shows complicated dynamics in both space and time.
no code implementations • 17 May 2017 • Biswa Sengupta, Karl Friston
In a published paper [Sengupta, 2016], we have proposed that the brain (and other self-organized biological and artificial systems) can be characterized via the mathematical apparatus of a gauge theory.
no code implementations • NeurIPS 2011 • Martin B. Stemmler, Biswa Sengupta, Simon Laughlin, Jeremy Niven
For a given height of an action potential, the least energy is consumed when the underlying currents obey the bang-bang principle: the currents giving rise to the spike should be intense, yet short-lived, yielding spikes with sharp onsets and offsets.