An Explicitly Relational Neural Network Architecture
Authors: Murray Shanahan, Kyriacos Nikiforou, Antonia Creswell, Christos Kaplanis, David Barrett, Marta Garnelo
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show that the proposed architecture, when pre-trained on a curriculum of such tasks, learns to generate reusable representations that better facilitate subsequent learning on previously unseen tasks when compared to a number of baseline architectures. |
| Researcher Affiliation | Collaboration | 1Deep Mind, London, UK 2Imperial College London, London, UK. Correspondence to: Murray Shanahan <mshanahan@google.com>. |
| Pseudocode | No | The paper describes the architecture and its components but does not provide a formal pseudocode or algorithm block. |
| Open Source Code | Yes | https://github.com/deepmind/deepmind-research/tree/master/PrediNet. |
| Open Datasets | No | Consequently, we devised a new configurable family of simple classification tasks that we collectively call the Relations Game. The paper describes the dataset but does not provide a specific link, DOI, or formal citation for public access to the generated datasets. The provided GitHub link is for the code, not explicitly the data. |
| Dataset Splits | No | The paper mentions 'held-out object sets' for testing but does not explicitly provide training/validation/test dataset splits (e.g., percentages, sample counts, or explicit standard splits) for reproducibility. |
| Hardware Specification | No | The paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers (e.g., Python, PyTorch, or CUDA versions) needed to replicate the experiment. |
| Experiment Setup | No | The paper mentions 'stochastic gradient descent' and 'Adam optimiser' and 'averages over 10 runs', and states that 'Further experimental details are given in the Supplementary Material', but does not provide specific hyperparameter values or comprehensive training configurations in the main text. |