Continual Learning with Deep Generative Replay

Authors: Hanul Shin, Jung Kwon Lee, Jaehong Kim, Jiwon Kim

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We test our methods in several sequential learning settings involving image classification tasks.
Researcher Affiliation Collaboration Hanul Shin Massachusetts Institute of Technology SK T-Brain skyshin@mit.edu Jung Kwon Lee , Jaehong Kim , Jiwon Kim SK T-Brain {jklee,xhark,jk}@sktbrain.com
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the methodology described.
Open Datasets Yes We tested our model on classifying MNIST handwritten digit database [19]. sequentially trained our model on classifying MNIST and Street View House Number (SVHN) dataset [25]
Dataset Splits No The paper mentions 'test data' and 'training' but does not explicitly describe training/test/validation dataset splits or mention a specific validation set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types) used for running its experiments.
Software Dependencies No The paper mentions techniques like WGAN-GP and GANs framework but does not provide specific software dependencies with version numbers (e.g., library names with versions).
Experiment Setup No The paper describes general training procedures and concepts like 'learning rates' and 'fine-tuning' but does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed system-level training settings.