Curso de Capacitação - Capítulo 4 - Deep Learning - Turma 2

A loss function is the same as a model function.

• True

• False

In a feedforward network, neurons in the same layer are connected to each other.

• True

• False

For the image classification problem, which of the following neural networks is more suitable to solve this problem?

• Sensor

• Recurrent neural network

• Convolutional Neural Network

• Fully connected neural network

Traditional machine learning and deep learning are the core technologies of artificial intelligence. There is a slight difference in the engineering process. Which of the following steps you don't need to do in deep learning is?

• Model evaluation

• Data cleansing

• Model building

• Feature engineering

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

• Convolutional layer

• Fully connected layer

• Pooling layer

• All of the above

In the process of training the neural network, our goal is to keep the loss function reduced. Which of the following methods do we usually use to minimize the loss function?

• Regularization

• Dropout

• Gradient descent

• Cross-validation

Unlike convolutional neural networks, recurrent neural networks are good at resolving:

• Sequence-related

• Image calculation

• Image test

• Recommendation problem

Currently, generative adversarial networks are widely used. Which of the following scenarios can use such networks?

• A. Image generationl

• Semantic generation

• Data augmentation

• Information retrieval

Convolutional neural networks are more suitable for dealing with speech recognition problems.

• True

• False

Which of the following descriptions about the Recurrent Neural Network (RNN) is correct?

• Unlike convolutional neural networks, parameters of RNN cannot be shared

• Can be used to process sequence data

• The units above the hidden layer are not associated with each other

• Cannot process variable length sequence data