Internet of Things for Architects

Training and inference for IoT

While neural networks offer significant advantages of having a machine behave closer to a human in the areas of perception, pattern recognition, and classification, it is primarily up to the training to develop a model that works well with low loss, no overfitting, and adequate performance. In the IoT world, latency is a large issue, especially for safety-critical infrastructure. Resource constraints is another factor. Most of the edge computing devices that exist today do not have hardware accelerators such as General-Purpose Computation on Graphics Hardware (GPGPU) and Field-programmable gate array (FPGAs) at their disposal to assist with the heavy matrix math and floating point surrounding neural networks. ...