I2dl sose2020

= Mock exam SoSe 2020 =


 * 1) How can you avoid overfitting?  solution
 * 2) What is the dropout technique?  solution
 * 3) What is Batch Normalization?  solution
 * 4) What optimization methods use first order momentum?  solution
 * 5) What happens when you add more parametrized layers to your neural network?  Neural Networks
 * 6) You're training a neural network and notice that the validation error is significantly lower than the training error. Name two possible reasons for this to happen.  Neural Networks
 * 7) "If you would use Newton-Method for optimization, your neural network would converge much faster than with gradient descent!"   solution
 * 8) Explain why we need activation functions.  solution
 * 1) Explain why we need activation functions.  solution
 * 1) Explain why we need activation functions.  solution