Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing World

Authors: Sahil Garg, Irina Rish, Guillermo Cecchi, Aurelie Lozano

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical evaluation on real-life datasets (images and text), as well as on synthetic data, demonstrates that the proposed approach can considerably outperform the state-of-art non-adaptive online sparse coding of [Mairal et al., 2009] in the presence of non-stationary data. Moreover, we identify certain dataand model properties associated with such improvements.
Researcher Affiliation Collaboration Sahil Garg , Irina Rish, Guillermo Cecchi, and Aurelie Lozano IBM Thomas J. Watson Research Center sahilgar@usc.edu, {rish, gcecchi, aclozano}@us.ibm.com
Pseudocode Yes Algorithm 1 Neurogenetic Online Dictionary Learning (NODL)
Open Source Code No The paper states 'The extended version of this paper is available at arxiv.org/abs/1701.06106,' which refers to the paper itself, not the source code for the methodology. No other statements or links regarding code availability are provided.
Open Datasets Yes Our first domain includes the images of Oxford buildings, i.e. urban environment 5, while the second uses a combination of images from Flowers 6 and Animals 7 image databases (natural environment). Footnotes provide URLs: 5 www.robots.ox.ac.uk/ vgg/data/oxbuildings/, 6 www.robots.ox.ac.uk/ vgg/data/flowers/102/, 7 www.robots.ox.ac.uk/ vgg/data/pets/.
Dataset Splits Yes We selected 5700 images for training and another 5700 for testing; each subset contained 1900 images of each type (i.e., Oxford, Flowers, Animals). In the training phase, the algorithms receive a sequence of 1900 samples from the first domain (Oxford), and then a sequence of 3800 samples from the second domain (1900 Flowers and 1900 Animals, permuted randomly); the batch size is 200 images.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments, such as GPU models, CPU types, or memory.
Software Dependencies No The paper does not list specific software dependencies with version numbers, such as programming language versions, libraries, or frameworks.
Experiment Setup Yes Parameter settings. We selected 5700 images for training and another 5700 for testing; each subset contained 1900 images of each type (i.e., Oxford, Flowers, Animals). In the training phase, the algorithms receive a sequence of 1900 samples from the first domain (Oxford), and then a sequence of 3800 samples from the second domain (1900 Flowers and 1900 Animals, permuted randomly); the batch size is 200 images ([Mairal et al., 2009] used a batch of size 256, though image patches rather than full images). We use Pearson correlation threshold γ = 0.9, group sparsity parameter λg = 0.03 and λg = 0.07, for 32x32 and 100x100 images, respectively; ck = 50 is the upper bound on the number of new dictionary elements at each iteration.