Top network posts

• 118 Why use gradient descent for linear regression, when a closed-form math solution is available?
• 115 Line of best fit does not look like a good fit. Why?
• 76 Why the sudden fascination with tensors?
• 57 Why is Newton's method not widely used in machine learning?
• 50 Are residuals "predicted minus actual" or "actual minus predicted"
• 45 Why doesn't regularization solve Deep Neural Nets hunger for data?
• 44 Approximate $e$ using Monte Carlo Simulation
• View more network posts →