easy5 pts · first answer countsdeep-learning
Why activation functions exist
Why do neural networks place non-linear activation functions (such as ReLU or GELU) between layers?
Discussion 0
Join free to post in the discussion.
Related questions
- A learning rate that is too highAI Engineer (LLM & Generative AI)
- Different results every inference runMachine Learning Engineer
- Early layers stop learningMachine Learning Engineer
- Initialisation for a deep ReLU networkMachine Learning Engineer
- Why fp16 needs loss scaling but bf16 usually does notMachine Learning Engineer