- weight
The weight tells us how much a given input influences the output.
weight告诉我们输入对输出的影响程度。 - bias
The bias is what the output would be if all inputs were zero.
bias表示当所有输入为0时的输出值。 - hyperparameter search
Systematically trying different values for learning rate, momentum, network size, and other similar configuration settings is called a hyperparameter search. - normalization
Normalizing each channel so that it has the same distribution will ensure that channel information can be mixed and updated through gradient descent using the same learning rate. - U-Net
The U-Net architecture is a design for a neural network that can produce pixelwise output and that was invented for segmentation.
摘抄自:Eli Stevens, Luca Antiga, Thomas Viehmann. Deep Learning with PyTorch.