What is one major drawback of using the sigmoid activation function in deep networks?
- Prone to vanishing gradient
- Limited to binary classification
- Efficiently handles negative values
- Non-smooth gradient behavior
One major drawback of using the sigmoid activation function in deep networks is its susceptibility to the vanishing gradient problem. This can hinder training deep networks as the gradient becomes very small for extreme values, slowing down learning.
Loading...
Related Quiz
- In CNNs, the layers that preserve the spatial relationships between pixels by learning image features through small squares of input data are called _______ layers.
- Which trend involves using AI to generate high-quality, realistic digital content?
- In the realm of Data Science, the library _______ in Python is widely used for data manipulation and cleaning.
- Which ensemble method adjusts weights for misclassified instances in iterative training?
- Which ETL tool provides native integrations with Apache Hadoop, Apache Spark, and other big data technologies?