Which risk increases when a neural network's activation functions saturate?

💡 Explanation

Vanishing gradients increase given activation function saturation because the derivative becomes near-zero and prevents learning via gradient descent. Therefore, the backpropagated error signal diminishes, rather than stronger, which stalls training even with powerful hardware.

• Which outcome results when high humidity reduces molecular hydrogen bonding in nylon fibers?
• Which outcome results when a catalyst with strong product affinity is introduced to a reversible reaction at equilibrium?
• Which outcome occurs when gravitational and inertial reaction tensors show equivalence?
• Which process enables 3D imaging in birefringent crystals?
• Which outcome results when free-fall ends inside a spacecraft?
• Which consequence results when thin-film interference affects solar cell performance?