Unverified50% confidenceFactExact time
A ReLU neuron that continuously receives negative input will permanently output 0 and cannot recover, i.e. the 'dead' neuron problem.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the Winner-Take-All mechanism, only one winning neuron is activated and updated for each input, which easily leads to dead units and limited representational capacity.67% similarUnverifiedRecommendations for choosing hidden layer activation functions: start with ReLU, and if a large number of neurons die, try Leaky ReLU; use Sigmoid for binary classification output; use Softmax for multi-class output; use no activation function for regression output.65% similarUnverifiedNeural networks exhibit permutation symmetry—reordering the neurons in a given layer leaves the network's functionality completely unchanged, as long as the weights of adjacent layers are adjusted accordingly.62% similarUnverified赫布定律指出一起激活的神经元连接在一起，长期不被激活的突触连接会在突触修剪过程中被清除61% similarUnverifiedAn artificial neuron receives multiple input signals, multiplies each input by a weight, adds a bias, and then passes the result through an activation function to determine whether to fire an output.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013756API
curl https://kongchang.com/api/v1/knowledge/claims/1013756MCP
get_claim(id=1013756)