muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems. (arXiv:2205.10937v2 [cs.LG] UPDATED)

Most uses of machine learning today involve training a model from scratch for
a particular task, or sometimes starting with a model pretrained on a related
task and then fine-tuning on a downstream task. Both approaches offer limited
knowledge transfer between different tasks, time-consuming human-driven
customization to individual tasks and high computational costs especially when
starting from randomly initialized models. We propose a method that uses the
layers of a pretrained deep neural network as building blocks to construct an …

arxiv networks neural networks scalable systems