no code implementations • ICLR 2019 • Ming-Chuan Yang, Meng Chang Chen
This work investigates the performance of a composite neural network, which is composed of pre-trained neural network models and non-instantiated neural network models, connected to form a rooted directed graph.
no code implementations • 22 Oct 2019 • Ming-Chuan Yang, Meng Chang Chen
In addition, if an extra pre-trained component is added to a composite network, with high probability, the overall performance will not be degraded.
no code implementations • 18 Oct 2019 • Ming-Chuan Yang, Meng Chang Chen
In this work, we prove that a composite neural network, with high probability, performs better than any of its pre-trained components under certain assumptions.