Deep Learning Overview

Which of the following options is not the reason why traditional machine learning algorithms promote the development of deep learning?

• dimension disaster

• local invariance and smooth regularization

• manifold learning

• feature engineering

Deep learning is different from machine learning, there is no unsupervised algorithm.

• True

• False

What are the regularization in deep learning?

• L1 norm L2 norm

• data set enhancement

• Integration method

• Dropout

Which of the following functions can numerically stabilize overflow and underflow?

• Softminux function

• Softplus function

• Softmax function

• Softmin function

Deep learning is a branch of machine learning.

• True

• False

What is wrong about the relationship between neural networks and deep learning?

• The concept of deep learning stems from the study of artificial neural networks

• a neural network algorithm with multiple hidden layers is a deep learning algorithm

• and a single-layer neural network is also a kind of deep learning

• convolutional neural network is a type of deep learning

What are the commonly used gradient descent optimization functions?

• stochastic gradient descent

• Adadelta

• Adagrad

• momentum

• RMSProp

What are the commonly used activation functions?

• sigmod

• tanh

• relu

• danish

A AI pioneer said that perceptron cannot process non-linear data. Who is he/she?

• Turing

• Simon

• Shannon

• Minsky

What is function which reflects the error between the target output and actual output of the perceptron?

• Perceptron function

• Actual function

• Output function

• Loss function