AI workshop-Day 4

QUESTION NO: 34

In the process of training the neural network, we use the gradient descent method to continuously update which value, which makes the loss Function minimization?

• Number of samples

• Eigenvalues

• Hyperparameter

• parameter

In the process of deep learning model training, what are the common optimizers?

• Adam

• Adagrad

• SGD

• Momentum

• all the above

In neural networks, weights are often shareD. Which of the following neural networks will share weights?

• a.sensor

• b.Convolutional Neural Network

• c. Fully connected neural network

• recurrent neural network

• BD

Convolutional neural networks are more suitable for image recognition problems than cyclic neural networks.

• TRUE

• FALSE

When training the network, we often encounter many problems. For the problem of gradient disappearance, we can alleviate the problem by choosing which of the following functions to use?

• Softsign function

• Relu function

• tanh function

• Sigmoid function

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

• Soft minus function

• Soft plus function

• Soft max function

• Softmin func!Jon

What is the incorrect relationship between neural networks and deep learning?

• The concept of deep learning sterns from the study or artificial neural networks.

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

• Single layer neural networks are also a type of deep learning

• Convolutional neural networks are a type of deep learning.

In the classic convolutional neural network model,Softmax What hidden layer does the function follow?

• Convolutional layer

• Pooling layer

• Fully connected layer

• All the above

If the deep learning neural network has the problem of gradient disappearance or gradient explosion, our common solution is.

• A. Gradient shear

• B. Random under sampling

• C. use Relu Activation function

• D. Regularization

• ACD

In deep learning tasks, when encountering data imbalance problems, which of the following methods can we use to solve the problem?

• A. batch deletion

• B. Random oversampling

• C. Synthetic sampling

• D. Random undersampling

• BCD