1 code implementation • 30 Jan 2024 • Luke Yang, Levin Kuhlmann, Gideon Kowadlo
Also, the concept of replay comes from biological inspiration, where evidence suggests that replay is applied to a world model, which implies model-based RL -- and model-based RL should have benefits for continual RL, where it is possible to exploit knowledge independent of the policy.
1 code implementation • 25 Jan 2024 • Jarrad Rinaldo, Levin Kuhlmann, Jason Friedman, Gideon Kowadlo
The models were trained and tested on two tasks common in the human motor control literature: the random reach task, suited to the dominant system, a model with better coordination, and the hold position task, suited to the non-dominant system, a model with more stable movement.
1 code implementation • 9 Sep 2022 • Chandramouli Rajagopalan, David Rawlinson, Elkhonon Goldberg, Gideon Kowadlo
We took a different approach and aimed to understand how dual hemispheres in a bilateral architecture interact to perform well in a given task.
1 code implementation • 26 Aug 2022 • Gideon Kowadlo, Abdelrahman Ahmed, Amir Mayan, David Rawlinson
Continual learning and few-shot learning are important frontiers in progress towards broader Machine Learning (ML) capabilities.
no code implementations • 15 Feb 2021 • Gideon Kowadlo, Abdelrahman Ahmed, David Rawlinson
The results demonstrated that with the addition of AHA, the system could learn in one-shot and consolidate the knowledge for the long term without catastrophic forgetting.
1 code implementation • 30 Oct 2020 • Gideon Kowadlo, Abdelrahman Ahmed, David Rawlinson
We propose an extension to the standard Omniglot classification-generalisation framework that additionally tests the ability to distinguish specific instances after one exposure and introduces noise and occlusion corruption.
no code implementations • 23 Sep 2019 • Gideon Kowadlo, Abdelrahman Ahmed, David Rawlinson
AHA is a biologically-plausible computational model of the Hippocampus.
no code implementations • 28 May 2019 • David Rawlinson, Abdelrahman Ahmed, Gideon Kowadlo
We present a recurrent neural network memory that uses sparse coding to create a combinatoric encoding of sequential inputs.
1 code implementation • 17 Apr 2018 • David Rawlinson, Abdelrahman Ahmed, Gideon Kowadlo
We show that unsupervised training of latent capsule layers using only the reconstruction loss, without masking to select the correct output class, causes a loss of equivariances and other desirable capsule qualities.