Unsupervised One-shot Learning of Both Specific Instances and Generalised Classes with a Hippocampal Architecture
This addresses a key limitation in machine learning for real-world tasks like object recognition, though it is incremental as it builds on existing frameworks and models.
The paper tackles the problem of one-shot learning that requires both generalizing within classes and distinguishing specific instances, proposing an unsupervised model based on Complementary Learning Systems. The model achieves comparable performance to supervised methods on Omniglot classification and significantly outperforms a baseline on instance recognition with noise and occlusion.
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. Distinguishing specific instances is necessary for many real-world tasks, such as remembering which cup belongs to you. Generalisation within classes conflicts with the ability to separate instances of classes, making it difficult to achieve both capabilities within a single architecture. 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. Learning is defined as an ability to classify as well as recall training samples. Complementary Learning Systems (CLS) is a popular model of mammalian brain regions believed to play a crucial role in learning from a single exposure to a stimulus. We created an artificial neural network implementation of CLS and applied it to the extended Omniglot benchmark. Our unsupervised model demonstrates comparable performance to existing supervised ANNs on the Omniglot classification task (requiring generalisation), without the need for domain-specific inductive biases. On the extended Omniglot instance-recognition task, the same model also demonstrates significantly better performance than a baseline nearest-neighbour approach, given partial occlusion and noise.