What Can Neural Networks Reason About?
Authors: Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
ICLR 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our theory is supported by empirical results. |
| Researcher Affiliation | Academia | Massachusetts Institute of Technology (MIT) University of Maryland Institute for Advanced Study (IAS) National Institute of Informatics (NII) |
| Pseudocode | No | The paper describes algorithms using prose and equations (e.g., in Figure 2 and Appendix G.3), but does not include formal pseudocode blocks or sections labeled 'Algorithm'. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing code or links to a code repository. |
| Open Datasets | Yes | One example from CLEVR (Johnson et al., 2017a) is How many objects are either small cylinders or red things? ... The Pretty-CLEVR dataset (Palm et al., 2018) is an extension of Sort-of-CLEVR (Santoro et al., 2017) and CLEVR (Johnson et al., 2017a). |
| Dataset Splits | Yes | In the dataset, we sample 50, 000 training data, 5, 000 validation data, and 5, 000 test data. |
| Hardware Specification | No | The paper does not provide specific details regarding the hardware used for experiments (e.g., GPU/CPU models, memory specifications). |
| Software Dependencies | No | The paper mentions software components like 'Adam optimizer' but does not specify version numbers for any libraries, frameworks, or programming languages used. |
| Experiment Setup | Yes | We train all models with the Adam optimizer, with learning rate from 1e 3, 5e 4, and 1e 4, and we decay the learning rate by 0.5 every 50 steps. We use cross-entropy loss. We train all models for 150 epochs. We tune batch size of 128 and 64. |