Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study
Authors: Mattia Medina Grespan, Ashim Gupta, Vivek Srikumar
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In our theoretical study driven by the goal of preserving tautologies, the Łukasiewicz t-norm performs best. However, in our empirical analysis on the text chunking and digit recognition tasks, the product t-norm achieves best predictive performance. |
| Researcher Affiliation | Academia | Mattia Medina Grespan , Ashim Gupta and Vivek Srikumar University of Utah {mattiamg,ashim,svivek}@cs.utah.edu |
| Pseudocode | No | The paper describes methods and processes using textual explanations and mathematical equations, but it does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | Yes | Our Py Torch [Paszke et al., 2019] code is archived at https:// github.com/utahnlp/neural-logic |
| Open Datasets | Yes | We use the popular MNIST dataset [Le Cun, 1998] for our experiments, but only to supervise the Digit classifier...Our second set of experiments use the NLP task of text chunking using the Co NLL 2000 dataset [Sang and Buchholz, 2000]. |
| Dataset Splits | Yes | We partition the 60k MNIST training images into TRAIN and DEV sets, with 50k and 10k images respectively. To supervise the Digit model, we sample 1k, 5k and 25k labeled images from TRAIN to form three DIGIT sets. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments, such as GPU models, CPU types, or memory specifications. It mentions using CNNs and LSTMs but no associated hardware. |
| Software Dependencies | No | The paper mentions 'PyTorch' but does not specify a version number or list any other software dependencies with their respective versions. |
| Experiment Setup | No | The paper mentions using a 'hyperparameter λ' and 'hyperparameter tuning' for the Digit and Arithmetic Operations task, but it does not specify concrete values for λ or other critical hyperparameters like learning rate, batch size, or number of epochs across any of its experiments. |