Computational Separation Between Convolutional and Fully-Connected Networks
Authors: eran malach, Shai Shalev-Shwartz
ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section we show some experiments that validate our theoretical results. In these experiments, the input to the network is a sequence of n MNIST digits, where each digit is scaled and cropped to a size of 24 8. |
| Researcher Affiliation | Academia | Eran Malach School of Computer Science Hebrew University Jerusalem, Israel eran.malach@mail.huji.ac.il Shai Shalev-Shwartz School of Computer Science Hebrew University Jerusalem, Israel shais@cs.huji.ac.il |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any specific repository links, explicit code release statements, or mention code in supplementary materials for the methodology described. |
| Open Datasets | Yes | To answer this question, we observe the performance of CNN and FCN based architecture of various widths and depths trained on the CIFAR-10 dataset. ... In these experiments, the input to the network is a sequence of n MNIST digits... |
| Dataset Splits | No | The paper mentions using CIFAR-10 and MNIST datasets and 'test accuracy', but does not provide specific details on the train, validation, and test dataset splits (e.g., percentages, sample counts, or explicit standard split citations) needed for reproduction. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions optimizers like 'RMSprop optimizer' and 'Ada Delta optimizer', and activation functions like 'Re LU', but does not provide specific version numbers for any software dependencies or libraries used to replicate the experiments. |
| Experiment Setup | Yes | trained for 125 epochs with RMSprop optimizer. In all the architectures we use a single hidden-layer with 1024 neurons, and Re LU activation. The networks are trained with Ada Delta optimizer for 30 epochs. |