deep-learning
Activation functions
taught
Taught in
-
A neuron is a weighted sum with a switch
Deep Learning / Neural Networks
-
Flat spots, and choosing an activation
Deep Learning / Neural Networks
Requires
- neuron-weight-and-bias required
Required by
- ReLU and its variants required
- Sigmoid and tanh required
- The sigmoid function required
- Why a neuron needs a nonlinear activation required
Local knowledge map
Local knowledge map
Click to expand
Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.