Corpus ID: 202719389

AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning

  title={AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning},
  author={G. Kowadlo and Abdelrahman Ahmed and David Rawlinson},
  • G. Kowadlo, Abdelrahman Ahmed, David Rawlinson
  • Published 2019
  • Computer Science, Biology, Mathematics
  • ArXiv
  • 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 is 'episodic' learning - the ability to rapidly memorize a specific experience as a composition of existing concepts, without provided labels. The new knowledge can then be used to distinguish between similar experiences, to generalize between classes, and to selectively consolidate to long-term memory. The… CONTINUE READING
    1 Citations

    Figures, Tables, and Topics from this paper.


    Complementary learning systems within the hippocampus: a neural network modelling approach to reconciling episodic memory with statistical learning
    • 115
    • PDF
    The storage and recall of memories in the hippocampo-cortical system
    • E. Rolls
    • Medicine, Biology
    • Cell and Tissue Research
    • 2017
    • 40
    • PDF
    Theta Coordinated Error-Driven Learning in the Hippocampus
    • 39
    • PDF
    Complementary Learning Systems
    • 138
    • PDF
    Overcoming catastrophic forgetting in neural networks
    • 1,336
    • PDF
    The CRISP theory of hippocampal function in episodic memory
    • S. Cheng
    • Psychology, Medicine
    • Front. Neural Circuits
    • 2013
    • 54
    • PDF
    Unsupervised Predictive Memory in a Goal-Directed Agent
    • 95
    • PDF
    Hippocampal Anatomy Supports the Use of Context in Object Recognition: A Computational Model
    • 11
    • PDF
    The mechanisms for pattern completion and pattern separation in the hippocampus
    • E. Rolls
    • Computer Science, Medicine
    • Front. Syst. Neurosci.
    • 2013
    • 233
    • PDF