Deploy Neural Network onto an Embedded Device

Deploy Neural Network onto an Embedded Device

Explore techniques for deploying neural networks on embedded devices in this 43-minute conference talk from code::dive 2022. Learn about pruning and quantization methods to optimize neural network performance on resource-constrained hardware. Gain insights from speaker Waqas Ahmad, an application engineer at The MathWorks with expertise in C/C++/CUDA code generation, fixed-point implementation, and software deployment on embedded systems. Discover practical approaches for implementing machine learning models in embedded applications, drawing from Ahmad's background in electrical engineering and signal processing, as well as his experience in the transportation industry.