Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Approximate Feature Collisions in Neural Nets
Authors: Ke Li, Tianhao Zhang, Jitendra Malik
NeurIPS 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section we will apply our method to two standard neural net architectures trained on the MNIST and Image Net datasets. The trained model achieves a test accuracy of 96.64%. |
| Researcher Affiliation | Academia | Ke Li UC Berkeley EMAIL Tianhao Zhang Nanjing University EMAIL Jitendra Malik UC Berkeley EMAIL |
| Pseudocode | No | The paper describes mathematical formulations and optimization problems but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions 'https://github.com/aymericdamien/TensorFlow-Examples' in a footnote, but this appears to be a general repository for TensorFlow examples and not the specific code implemented for the methodology described in this paper. |
| Open Datasets | Yes | First we train a simple fully-connected neural network with two hidden layers... on the MNIST dataset. We now perform the same experiment on Image Net. |
| Dataset Splits | No | The paper mentions training on MNIST and Image Net datasets and reports test accuracy, but it does not provide specific details regarding train/validation/test dataset splits (e.g., percentages, sample counts, or splitting methodology). |
| Hardware Specification | No | The paper does not explicitly describe the hardware specifications (e.g., specific GPU/CPU models, memory, or cloud instances) used for running its experiments. |
| Software Dependencies | No | The paper mentions 'TensorFlow' in a footnote but does not provide specific version numbers for TensorFlow or any other software libraries or dependencies used. |
| Experiment Setup | No | The paper describes neural network architectures used (e.g., 'fully-connected neural network with two hidden layers' for MNIST, 'pre-trained VGG-16 net' for Image Net) but does not provide specific experimental setup details such as hyperparameters (learning rate, batch size, epochs, optimizer settings) or training configurations. |