Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Training DNNs with Hybrid Block Floating Point
Authors: Mario Drumond, Tao LIN, Martin Jaggi, Babak Falsafi
NeurIPS 2018 | Venue PDF | LLM Run Details | Input Tokens: 15,719 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,785 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We experiment with a set of popular image classification tasks with the CIFAR-100, SVHN, and Image Net datasets. |
| Researcher Affiliation | Academia | Mario Drumond Ecocloud EPFL EMAIL Tao Lin Ecocloud EPFL EMAIL Martin Jaggi Ecocloud EPFL EMAIL Babak Falsafi Ecocloud EPFL EMAIL |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology. |
| Open Datasets | Yes | We experiment with a set of popular image classification tasks with the CIFAR-100 [19], SVHN [20], and Image Net [21] datasets. We also evaluate language modeling tasks with Penn Tree Bank(PTB) dataset [24]. |
| Dataset Splits | No | For the image classification experiments, we report training loss and validation top-1 error. For the language modeling models, we report training loss and validation perplexity. While these datasets have standard splits, the paper doesn't explicitly state what splits were used for reproducibility. |
| Hardware Specification | Yes | We synthesize the accelerator on a Stratix V 5SGSD5 FPGA at a clock rate of 200MHz. |
| Software Dependencies | No | The paper mentions modifying Py Torch's layers but does not specify the version number of Py Torch or any other software dependencies with their versions. |
| Experiment Setup | No | The paper states, 'We trained all models using the same hyperparameters reported in their respective original papers,' which means the specific hyperparameter values are not directly provided within this paper. |