Chapter 1 - Introduction - 三种趋势

    xiaoxiao2021-03-26  9

    1.2.2 Increasing Dataset Sizes

    As of 2016, a rough rule of thumb is that a supervised deep learning algorithm will generally achieve acceptable performance with around 5,000 labeled examples per category, and will match or exceed human performance when trained with a dataset containing at least 10 million labeled examples.

    1.2.3 Increasing Model Sizes

    Even today’s networks, which we consider quite large from a computational systems point of view, are smaller than the nervous system of even relatively primitive vertebrate animals like frogs.

    1.2.4 Increasing Accuracy, Complexity and Real-World Impact

    In recent years, it has seen tremendous growth in its popularity and usefulness, due in large part to more powerful com- puters, larger datasets and techniques to train deeper networks.