Alternating Least Squares (ALS) Recomendation Engine
The Als_kernel is used for the training of Recomendation engines , It is produced with SDSoC 2016.2 version. The code provided in this folder is a C-based implementation of 'Alternating Least Squares Training Algorithm' for Recomendation, optimised for ZED board, and is a case study of FPGA-Accelerated Machine Learning. The algorith in its current form supports only explicit feedback .
Testing Als source in Software
make(also extracts datasets)
- (optional) Edit run.sh
- run using
Testing Als in Hardware
The C source files are provided here without project files, but they contain HLS/SDS directives specific to Xilinx SDSoC.
If you want to create a SDSoC project using these sources you may find the following instructions helpful:
- Launch SDSoC and create a new empty project. Choose
zedas target platform.
- Add the C sources in
topLevelHwas hardware function. Set clock frequency at
- All design parameters are set in the file
Generate SD Card Image.
Performance using 80 Features
|Dataset||Software only exececution (ZedBoard)||Software-Hardware Execution (ZedBoard)||Speed-Up|
For any question or discussion, please contact the authors: