官术网_书友最值得收藏!

Balanced dataset

The application allows you to record samples of different motion types. As you train the model, you may notice one interesting effect: to get accurate predictions, you need not only enough samples, but you also need the proportion of different classes in your dataset to be roughly equal. Think about it: if you have 100 samples of two classes (walk and run), and 99 of them belong to one class (walk), the classifier that delivers 99% accuracy may look like this:

func predict(x: [Double]) -> MotionType { 
   return .walk 
} 

But this is not what we want, obviously.

This observation lead us to the notion of the balanced data set; for most machine learning algorithms, you want the data set in which samples of different classes are represented equally frequently.

主站蜘蛛池模板: 永济市| 九龙坡区| 崇明县| 武平县| 彰化市| 葫芦岛市| 宝山区| 烟台市| 偏关县| 怀来县| 华坪县| 工布江达县| 万州区| 屏南县| 衡阳市| 靖州| 米泉市| 平凉市| 泗阳县| 旌德县| 西青区| 洛宁县| 慈利县| 普安县| 岑巩县| 泽库县| 韩城市| 磐安县| 白朗县| 高安市| 虹口区| 高雄县| 溧阳市| 和政县| 惠州市| 那坡县| 荥经县| 五寨县| 黄陵县| 永靖县| 章丘市|