Using synthetic data to train neural networks is model-based reasoning

TA Le, AG Baydin, R Zinkov… - 2017 international joint …, 2017 - ieeexplore.ieee.org
We draw a formal connection between using synthetic training data to optimize neural
network parameters and approximate, Bayesian, model-based reasoning. In particular,
training a neural network using synthetic data can be viewed as learning a proposal
distribution generator for approximate inference in the synthetic-data generative model. We
demonstrate this connection in a recognition task where we develop a novel Captcha-
breaking architecture and train it using synthetic data, demonstrating both state-of-the-art …

Using Synthetic Data to Train Neural Networks is Model− Based Reasoning

AG Baydin - 2017 - cs.ox.ac.uk
We draw a formal connection between using synthetic training data to optimize neural
network parameters and approximate, Bayesian, model-based reasoning. In particular,
training a neural network using synthetic data can be viewed as learning a proposal
distribution generator for approximate inference in the synthetic-data generative model. We
demonstrate this connection in a recognition task where we develop a novel Captcha-
breaking architecture and train it using synthetic data, demonstrating both state-of-the-art …
以上显示的是最相近的搜索结果。 查看全部搜索结果