45 citations · 59 across the 14 of their papers we have counts for
14 papers
In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models
Benjamin Smith, Levin Kuhlmann, Kaushik Roy +1
Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared to biological lea…
Communication in modular robotic motor control: Bilateral controllers under realistic constraints
Jingwen Li, Levin Kuhlmann, Jason Friedman +1
Robotic motor control in musculoskeletal systems requires fast, accurate movement and robust postural stabilization under signal-dependent noise (where motor command variance scale…
ARROW: Augmented Replay for RObust World models
Abdulaziz Alyahya, Abdallah Al Siyabi, Markus R. Ernst +3
Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future task…
Active perception and disentangled representations allow continual, episodic zero and few-shot learning
David Rawlinson, Gideon Kowadlo
Generalization is often regarded as an essential property of machine learning systems. However, perhaps not every component of a system needs to generalize. Training models for gen…
Graceful task adaptation with a bi-hemispheric RL agent
Grant Nicholas, Levin Kuhlmann, Gideon Kowadlo
In humans, responsibility for performing a task gradually shifts from the right hemisphere to the left. The Novelty-Routine Hypothesis (NRH) states that the right and left hemisphe…
Augmenting Replay in World Models for Continual Reinforcement Learning
Luke Yang, Levin Kuhlmann, Gideon Kowadlo
Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorit…
Left/Right Brain, human motor control and the implications for robotics
Jarrad Rinaldo, Levin Kuhlmann, Jason Friedman +1
Neural Network movement controllers promise a variety of advantages over conventional control methods, however, they are not widely adopted due to their inability to produce reliab…
Expanding continual few-shot learning benchmarks to include recognition of specific instances
Gideon Kowadlo, Abdelrahman Ahmed, Amir Mayan +1
Continual learning and few-shot learning are important frontiers in progress toward broader Machine Learning (ML) capabilities. Recently, there has been intense interest in combini…
Deep learning in a bilateral brain with hemispheric specialization
Chandramouli Rajagopalan, David Rawlinson, Elkhonon Goldberg +1
The brains of all bilaterally symmetric animals on Earth are divided into left and right hemispheres. The anatomy and functionality of the hemispheres have a large degree of overla…
One-shot learning for the long term: consolidation with an artificial hippocampal algorithm
Gideon Kowadlo, Abdelrahman Ahmed, David Rawlinson
Standard few-shot experiments involve learning to efficiently match previously unseen samples by class. We claim that few-shot learning should be long term, assimilating knowledge…
Unsupervised One-shot Learning of Both Specific Instances and Generalised Classes with a Hippocampal Architecture
Gideon Kowadlo, Abdelrahman Ahmed, David Rawlinson
Established experimental procedures for one-shot machine learning do not test the ability to learn or remember specific instances of classes, a key feature of animal intelligence.…
AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning
Gideon Kowadlo, Abdelrahman Ahmed, David Rawlinson
The majority of ML research concerns slow, statistical learning of i.i.d. samples from large, labelled datasets. Animals do not learn this way. An enviable characteristic of animal…
Learning distant cause and effect using only local and immediate credit assignment
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. Using several examples, we show that the network can as…
Sparse Unsupervised Capsules Generalize Better
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 a…