5 papers
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.…
Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling
Jeremy Gordon, David Rawlinson, Subutai Ahmad
In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as…
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…
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…