Topic 1 Question 3
You were asked to investigate failures of a production line component based on sensor readings. After receiving the dataset, you discover that less than 1% of the readings are positive examples representing failure incidents. You have tried to train several classification models, but none of them converge. How should you resolve the class imbalance problem?
Use the class distribution to generate 10% positive examples.
Use a convolutional neural network with max pooling and softmax activation.
Downsample the data with upweighting to create a sample with 10% positive examples.
Remove negative examples until the numbers of positive and negative examples are equal.
ユーザの投票
コメント(17)
- less than 1% of the readings are positive
- none of them converge.
Downsampling (in this context) means training on a disproportionately low subset of the majority class examples.
👍 27celia202004102021/07/19=New Question3= You are going to train a DNN regression model with Keras APJs using this code:
model - tf.keras.Sequential() model.add(tf.keras.layers.Oense( 256, use_bias-True, activation-•relu', kernel_initializer-None, kernel_regularizer-None, input_shape-(500,))) model.add(tf.keras.layers.Oropout(rate-0.25)) model.add(tf.keras.layers.Oense( 128, use_bias-True, activation-•relu', kernel_initializer-'uniform', kernel_regularizer-'12')) model.add(tf.keras.layers.Oropout(rate-0.25)) model.add(tf.keras.layers.Oense( 2, use_bias-False, activation-•softriax')) model.cornpile(loss-•mse') How many trainable weights does your model have? (The arithmetic below is correct.)A. 501256+257128+2 = 161154 B. 500256+256128+1282 = 161024 C. 501256+257128+1282 = 161408 D. 5002560(?)25+2561280(?)25+128*2 = 4044
👍 7MisterHairy2021/12/22Option C is my choice.
Downsampling (in this context) means training on a disproportionately low subset of the majority class examples.
Upweighting means adding an example weight to the downsampled class equal to the factor by which you downsampled.
👍 1alphard2021/12/06
シャッフルモード