# Image Classification on CIFAR-10 (test) (Accuracy and Backprop Difference)

Source: [Image Classification on CIFAR-10 (test) (Accuracy and Backprop Difference)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-and-backprop-difference>)

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

Data updated: 2026-02-26T05:30:45.006Z

Evaluation of Image Classification performance on the CIFAR-10 test set, reporting standard Accuracy alongside the difference relative to standard backpropagation results.

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) | CIFAR-10 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-and-backprop-difference.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Backprop Difference](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-and-backprop-difference.md?metric=Backprop%20Difference>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| E2E BP | 86.98 | Not recorded | 697c3b00a8b01e76cc8da442 |
| GHL | 86.41 | Not recorded | 697c3b00a8b01e76cc8da442 |
| E2E BP | 84.71 | Not recorded | 697c3b00a8b01e76cc8da442 |
| GHL | 83.96 | Not recorded | 697c3b00a8b01e76cc8da442 |
| SoftHebb | 80.36 | Not recorded | 697c3b00a8b01e76cc8da442 |
| HPCA-FH | 67.73 | Not recorded | 697c3b00a8b01e76cc8da442 |
| SWTA-FH | 55.23 | Not recorded | 697c3b00a8b01e76cc8da442 |

### E2E BP

Accuracy: 86.98. Result ID: 69961a4f5698665ec45a4a8c.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

Recorded evaluation configuration: {"Arch":"DeepHebb"}. This record does not assert independent reproduction.

### GHL

Accuracy: 86.41. Result ID: 69961a4f5698665ec45a4a8b.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

Recorded evaluation configuration: {"Arch":"DeepHebb"}. This record does not assert independent reproduction.

### E2E BP

Accuracy: 84.71. Result ID: 69961a4f5698665ec45a4a90.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

Recorded evaluation configuration: {"Arch":"FastHebb"}. This record does not assert independent reproduction.

### GHL

Accuracy: 83.96. Result ID: 69961a4f5698665ec45a4a8f.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

Recorded evaluation configuration: {"Arch":"FastHebb"}. This record does not assert independent reproduction.

### SoftHebb

Accuracy: 80.36. Result ID: 69961a4f5698665ec45a4a8a.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f4e1e209131ce9e8dda.md>)

Recorded evaluation configuration: {"Arch":"DeepHebb"}. This record does not assert independent reproduction.

### HPCA-FH

Accuracy: 67.73. Result ID: 69961a4f5698665ec45a4a8e.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

Recorded evaluation configuration: {"Arch":"FastHebb"}. This record does not assert independent reproduction.

### SWTA-FH

Accuracy: 55.23. Result ID: 69961a4f5698665ec45a4a8d.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b00a8b01e76cc8da442.md>)

Recorded evaluation configuration: {"Arch":"FastHebb"}. This record does not assert independent reproduction.

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