Recurrent Models of Visual Attention
Authors: Volodymyr Mnih, Nicolas Heess, Alex Graves, koray kavukcuoglu
NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our model on several image classification tasks, where it significantly outperforms a convolutional neural network baseline on cluttered images, and on a dynamic visual control problem, where it learns to track a simple object without an explicit training signal for doing so. |
| Researcher Affiliation | Industry | Volodymyr Mnih Nicolas Heess Alex Graves Koray Kavukcuoglu Google Deep Mind {vmnih,heess,gravesa,korayk} @ google.com |
| Pseudocode | No | The paper describes the model architecture and training procedure in text and diagrams but does not include explicit pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide a link or statement about open-sourcing the code for the described methodology. |
| Open Datasets | Yes | We first tested the ability of our training method to learn successful glimpse policies by using it to train RAM models with up to 7 glimpses on the MNIST digits dataset. |
| Dataset Splits | No | The paper mentions using a 'test set' but does not specify explicit training, validation, or test split percentages or counts for the datasets used. |
| Hardware Specification | No | The paper mentions training on 'multiple GPUs' but does not provide specific hardware details such as GPU models, CPU specifications, or memory. |
| Software Dependencies | No | The paper describes software components conceptually (e.g., 'stochastic gradient descent') but does not specify software names with version numbers. |
| Experiment Setup | Yes | All methods were trained using stochastic gradient descent with minibatches of size 20 and momentum of 0.9. We annealed the learning rate linearly from its initial value to 0 over the course of training. Hyperparameters such as the initial learning rate and the variance of the location policy were selected using random search [3]. |