DistillPrep
PythonGenAIGenAI FrameworksNLPDeep LearningMachine LearningML LibrariesStatisticsSQLMLOpsCloudSystem Design
Blog
D

Deep Learning

Curriculum Engine

Knowledge Tracks

Mastery Insight

"Focus on topics where you've failed edge-case questions. MAANG interviewers look for conceptual depth, not speed."

Live Engine
Select Topic
easyNeurons And Perceptrons
A neural network layer computes z = Wx + b, where W is a 64×128 weight matrix, x is a 128-dimensional input, and b is a 64-dimensional bias. A new engineer adds an extra bias vector of shape (64,) after the activation and trains the model. He is surprised to find no improvement. What is the most likely reason?
Progress0%
0 of 240 concepts cleared
Accuracy
0%
Solved
0

Question Index

Interview Tips

  • 1.Concepts over memorization.
  • 2.Identify trade-offs in every solution.