i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

Authors: Xinyang Zhang, Ren Pang, Shouling Ji, Fenglong Ma, Ting Wang11691-11698

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We prototype i-Algebra and conduct user studies in a set of representative analysis tasks, including inspecting adversarial inputs, resolving model inconsistency, and cleansing contaminated data, all demonstrating its promising usability.
Researcher Affiliation Academia Xinyang Zhang,1 Ren Pang,1 Shouling Ji,2 Fenglong Ma,1 Ting Wang1 1Pennsylvania State University, 2Zhejiang University
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks. It describes operators and a query language but not in a formal pseudocode format.
Open Source Code No The paper does not provide concrete access to source code for the methodology described. There is no mention of a repository link, an explicit code release statement, or code being available in supplementary materials.
Open Datasets Yes Setting On CIFAR10, we train two VGG19 models f and f. [...] Setting We use Image Net as the dataset and consider a pre-trained Res Net50 (77.15% top-1 accuracy) as the target DNN.
Dataset Splits No The paper references datasets like CIFAR10 but does not provide specific train/validation/test dataset splits (percentages or counts) that were used during model training to reproduce the experiment.
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments, lacking specific GPU/CPU models, processor types, or detailed computer specifications.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., Python version, PyTorch/TensorFlow version, or other library versions) needed to replicate the experiment.
Experiment Setup No The paper mentions training models (VGG19) and using pre-trained models (ResNet50) but does not provide specific experimental setup details such as hyperparameter values (learning rate, batch size, epochs), optimizer settings, or other training configurations.