Continual Unsupervised Representation Learning

Authors: Dushyant Rao, Francesco Visin, Andrei Rusu, Razvan Pascanu, Yee Whye Teh, Raia Hadsell

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 4 Experiments, We demonstrate the efficacy of CURL in an unsupervised learning setting with MNIST and Omniglot, We evaluate this using cluster accuracy, We perform an ablation study to gauge the impact of the expansion threshold for continual learning, in terms of cluster accuracy and number of components used, as shown in Figure 3. The results in Table 3 demonstrate that the proposed unsupervised approach can easily and effectively be adapted to supervised tasks, achieving competitive results for both scenarios.
Researcher Affiliation Industry Dushyant Rao, Francesco Visin, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu, Raia Hadsell Deep Mind London, UK
Pseudocode No The paper contains mathematical equations and diagrams, but no structured pseudocode or algorithm blocks are present.
Open Source Code Yes Code for all experiments can be found at https://github.com/deepmind/deepmind-research/.
Open Datasets Yes For the evaluation we extensively utilise the MNIST (Le Cun et al., 2010) and Omniglot (Lake et al., 2011) datasets, and further information can be found in Appendix B.
Dataset Splits No The paper mentions 'training' and 'validation' in the context of model components and processes (e.g., 'during training', 'model validation'), but it does not provide specific numerical details (percentages or counts) for dataset splits for training, validation, or testing in the main text. It defers these details to Appendix C.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments, such as GPU or CPU models, or cloud computing instance types.
Software Dependencies No The paper does not specify software dependencies with version numbers (e.g., specific programming language versions or library versions).
Experiment Setup No The paper explicitly states that 'further experimental details can be found in Appendix C.1' and 'full details of the experimental setup can be found in Appendix C.3', indicating that specific experimental setup details, such as hyperparameters or training configurations, are not provided in the main text.