# Image Classification on MNIST Large 784-392-196-10 (test)

Source: [Image Classification on MNIST Large 784-392-196-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-23T07:44:14.107Z

Evaluation of Image Classification performance and hardware utilization (Accuracy, LUTs, FFs, DSPs, BRAMs, Power, Latency) for the specific MNIST Large model configuration (784-392-196-10) on the test set.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Classification |
| Dataset (including any stated split) | MNIST Large 784-392-196-10 (test) |
| Metric | Reference Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Reference Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test.md?metric=Reference%20Accuracy>): Higher is better; unit: PERCENT.

- [Hardware Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test.md?metric=Hardware%20Accuracy>): Higher is better; unit: PERCENT.

- [LUTs](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test.md?metric=LUTs>): Lower is better; unit: SIZE.

- [FFs](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test.md?metric=FFs>): Lower is better; unit: SIZE.

- [DSPs](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test.md?metric=DSPs>): Lower is better; unit: SIZE.

- [BRAMs](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test.md?metric=BRAMs>): Lower is better; unit: SIZE.

- [Power (mW)](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test.md?metric=Power%20(mW)>): Lower is better; unit: OTHER.

- [Latency (ms)](<https://www.sota2.com/research/sota/image-classification-on-mnist-large-784-392-196-10-test.md?metric=Latency%20(ms)>): Lower is better; unit: TIME.

## Recorded results

| Method | Reference Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| VQ4SNN | 94.38 | Not recorded | 6a3a1306206542251d7c6f00 |
| ModNEF | 93.2 | Not recorded | 6a3a1306206542251d7c6f00 |

### VQ4SNN

Reference Accuracy: 94.38. Result ID: 6a3a390ffbc373592c342949.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1306206542251d7c6f00.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a1306206542251d7c6f00.md>)

Recorded evaluation configuration: {"Design":"Proposed","Config":"L1:d=8 k=2^11 L2:d=8 k=2^11","Network Type":"FC-FF-R","Weight bits":"8","Memb. Potential bits":"15","Spikes time-steps":"25"}. This record does not assert independent reproduction.

### ModNEF

Reference Accuracy: 93.2. Result ID: 6a3a390ffbc373592c342948.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1306206542251d7c6f00.md>)

Recorded evaluation configuration: {"Design":"ModNEF","Network Type":"FC-FF","Weight bits":"8","Memb. Potential bits":"16","Spikes time-steps":"100"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
