We lifted 6 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| hls-fpga-machine-learning/hls4ml | canonical | 3 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| array_to_summary | Ran | hls-fpga-machine-learning/hls4ml/hls4ml/model/profiling.py code served (permissive licence) · get_code("254e7a84dc620a57") |
| boxplot | Ran | hls-fpga-machine-learning/hls4ml/hls4ml/model/profiling.py code served (permissive licence) · get_code("f5cba7fafe8166fd") |
| find_minimum_width | Ran | hls-fpga-machine-learning/hls4ml/hls4ml/model/types.py code served (permissive licence) · get_code("bee79d98e7582bd9") |
| fetch_example_model | Not yet run | hls-fpga-machine-learning/hls4ml/hls4ml/utils/example_models.py code served (permissive licence) · get_code("8ff9eaa80ce13603") |
| get_backend | Not yet run | hls-fpga-machine-learning/hls4ml/hls4ml/backends/backend.py code served (permissive licence) · get_code("1242fc9c36f9fde0") |
| get_unoptimized_hlsmodel | Not yet run | hls-fpga-machine-learning/hls4ml/hls4ml/model/profiling.py code served (permissive licence) · get_code("a0f249e116bdec49") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with floating point precision, we investigate different strategies to reduce the network's resource consumption by reducing the numerical precision of the network parameters to binary or ternary. We discuss the trade-off between model accuracy and resource consumption. In addition, we show how to balance between latency and accuracy by retaining full precision on a selected subset of network components. As an example, we consider two multiclass classification tasks: handwritten digit recognition with the MNIST data set and jet identification with simulated proton-proton collisions at the CERN Large Hadron Collider. The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2003.06308")
get_code_for_paper("2003.06308")
have("2003.06308")
Connect an agent — have() is free.