medium10 pts · first answer countsinitializationdeep-learning
Initialisation for a deep ReLU network
Which weight initialisation is the standard choice for a deep network with ReLU activations?
Discussion 0
Join free to post in the discussion.
Related questions
- Different results every inference runMachine Learning Engineer
- Early layers stop learningMachine Learning Engineer
- Why fp16 needs loss scaling but bf16 usually does notMachine Learning Engineer
- Why activation functions existAI Engineer (LLM & Generative AI)
- A learning rate that is too highAI Engineer (LLM & Generative AI)