COURSE 1: CREATE MACHINE LEARNING MODELS IN MICROSOFT AZURE

Module 3: Train And Evaluate Deep Learning Models

MICROSOFT AZURE DATA SCIENTIST ASSOCIATE (DP-100) PROFESSIONAL CERTIFICATE

Complete Coursera Study Guide

Enroll in Coursera Microsoft Azure Data Scientist Associate (DP-100)

Last updated:

TABLE OF CONTENT

INTRODUCTION – Train And Evaluate Deep Learning Models

In this module, you will delve into the fundamental principles of deep learning, gaining a comprehensive understanding of how these principles underpin the creation of sophisticated neural network models. You will be guided through the process of building deep neural networks using popular frameworks such as PyTorch and TensorFlow.

Furthermore, the module will provide an in-depth exploration of convolutional neural networks (CNNs), focusing on their application in developing advanced image classification models. By the end of this module, you will have the knowledge and skills to effectively utilize these powerful tools in various deep learning tasks.

Learning Objectives

  • Basic principles of deep learning
  • How to train a deep neural network (DNN) using PyTorch or Tensorflow
  • How to use transfer learning to train a convolutional neural network (CNN) with PyTorch or Tensorflow
  • How to train a convolutional neural network (CNN) using PyTorch or Tensorflow

PRACTICE QUIZ: KNOWLEDGE CHECK 1

1. Complete the sentence:

Deep learning is an advanced form of machine learning that aims to[…]?

  • Help humans develop better learning skills.
  • Emulate the way the human brain learns. (CORRECT)
  • Make machines learn better and faster than humans.

Correct: Deep learning emulates this biological process using artificial neural networks that process numeric inputs rather than electrochemical stimuli.

2. In a deep learning model, the incoming nerve connections are emulated by numeric inputs which are typically identified as x.

Each x value is associated with some inputs. Which are those inputs?

  • Speed
  • Ratio
  • Weight (CORRECT)
  • Bias (CORRECT)

Correct: Feedback: weight (w) input is used to strengthen or weaken the effect of the x value to simulate learning.

Correct: Feedback: bias (b) input is added to enable fine-grained control over the network. 

3. The training process of a deep neural network consists of multiple iterations.

What is the name of those iterations?

  • Epochs (CORRECT)
  • Eras
  • Cycles

Correct: They’re called epochs.

4. During the training of a deep neural network, inside an epoch, in which step is the loss calculated?

  • 3rd  (CORRECT)
  • 1st
  • 4th
  • 2nd

Correct: The third step is where the prediction is compared to the actual known value, and the amount of variance between the predicted and true values (which we call the loss) is calculated.

5. True or False?

When training deep learning models, computers with GPUs perform better than computers with CPUs only.

  • True (CORRECT)
  • False

Correct: Linear algebraic functions that operate with matrices and vectors also feature in 3D graphics processing, which is why computers with GPUs provide significantly better performance for deep learning model training than CPU only computers.

PRACTICE QUIZ: KNOWLEDGE CHECK

1. In which AI domain are deep learning models particularly useful?

  • Speech processing
  • Image processing (CORRECT)
  • Text processing
  • Natural language processing (NLP)

Correct: While you can use deep learning models for any kind of machine learning, they’re particularly useful for dealing with data that consists of large arrays of numeric values – such as images. Machine learning models that work with images are the foundation for an area artificial intelligence called computer vision, and deep learning techniques have been responsible for driving amazing advances in this area over recent years.

2. How does a convolutional neural network typically work?

  • By comparing features and known labels to generate a prediction
  • By grouping objects based on similar features
  • By extracting features from images and feeding them into a network to generate a prediction (CORRECT)

Correct: Specifically, a CNN works by extracting features from images, and then feeding those features into a fully connected neural network to generate a prediction. The feature extraction layers in the network have the effect of reducing the number of features from the potentially huge array of individual pixel values to a smaller feature set that supports label prediction.

3. A convolutional network consists of multiple layers.

Which are those layers?

  • Scanning layers
  • Curving layers
  • Dropping layers (CORRECT)
  • Fully connected layers (CORRECT)
  • Pooling layers (CORRECT)
  • Flattening layers (CORRECT)
  • Convolution layers (CORRECT)

Correct: One technique you can use to mitigate overfitting is to include layers in which the training process randomly eliminates (or “drops”) feature maps.

Correct: Feedback: Usually, a CNN ends with a fully connected network in which the feature values are passed into an input layer, through one or more hidden layers, and generate predicted values in an output layer.

Correct: After extracting feature values from images, pooling (or downsampling) layers are used to reduce the number of feature values while retaining the key differentiating features that have been extracted.

Correct: A flattening layer is used to flatten the feature maps into a vector of values that can be used as input to a fully connected layer.

Correct: One of the principal layer types is a convolutional layer that extracts important features in images.

4. Which convolutional network layer helps ensure that the model doesn’t become over-dependent on the training images?

  • Dropping layer (CORRECT)
  • Flattening layer
  • Fully connected layer

Correct: One of the most difficult challenges in a CNN is the avoidance of overfitting, where the resulting model performs well with the training data but doesn’t generalize well to new data on which it wasn’t trained. One technique you can use to mitigate overfitting is to include layers in which the training process randomly eliminates (or “drops”) feature maps. This may seem counterintuitive, but it’s an effective way to ensure that the model doesn’t learn to be over-dependent on the training images.

5. True or False?

A convolutional layer applies multiple filter kernels, where each filter produces a different feature map, and all of the feature maps are passed onto the next layer of the network.

  • True (CORRECT)
  • False

Correct: A convolutional layer works by applying a filter to images. The filter is defined by a kernel that consists of a matrix of weight values.

QUIZ: TEST PREP

1. You developed a deep neural network to train a classification model that predicts to which of the four classes an observation belongs based on 8 numeric features. 

Which of the following statements is true about the network architecture?

  • The network layer should contain four hidden layers
  • The input layer should contain four nodes
  • The output layer should contain four nodes (CORRECT)

Correct: The output layer should contain a node for each possible class value.

2. You are training a deep neural network. You configured the training process to use 35 epochs.

What effect does this have on the behavior of the model?

  • The training data is split into 35 subsets, and each subset is passed through the network.
  • The first 35 rows of data are used to train the model, and the remaining rows are used to validate it.
  • The entire training dataset is passed through the network 35 times. (CORRECT)

Correct: The number of epochs determines the number of training passes for the full dataset.

3. When creating a deep neural network, if you increase the Learning Rate parameter, what effect will this setting have?

  • More hidden layers are added to the network.
  • Larger adjustments are made to weight values during backpropagation. (CORRECT)
  • More records are included in each batch passed through the network.

Correct: Increasing the learning rate causes backpropagation to make larger weight adjustments.

4. When creating a convolutional neural network, if you want to reduce the size of the feature maps that are generated by a convolutional layer, what should you do?

  • Reduce the size of the filter kernel used in the convolutional layer.
  • Add a pooling layer after the convolutional layer. (CORRECT)
  • Increase the number of filters in the convolutional layer.

Correct: A pooling layer reduces the number of features in a feature map.

5. True or False?

The feature extraction layers apply convolutional filters and pooling to emphasize edges, corners, and other patterns in the images that can be used to differentiate them, and in theory should work for any set of images with the same dimensions as the input layer of the network.

  • True (CORRECT)
  • False

Correct: The feature extraction layers apply convolutional filters and pooling to emphasize edges, corners, and other patterns in the images that can be used to differentiate them, and in theory should work for any set of images with the same dimensions as the input layer of the network.

6. This layer is a principal layer type that extracts important features in images. It works by applying a filter to images. What type of layer is this?

  • Flattening layer
  • Convulsion layer (CORRECT)
  • Pooling layer

Correct: One of the principal layer types is a convolutional layer that extracts important features in images. A convolutional layer works by applying a filter to images.

7. After extracting feature values from images, this layer is used to reduce the number of feature values while retaining the key differentiating features that have been extracted.

  • Flattening layer
  • Convulsion layer
  • Pooling layer (CORRECT)

Correct: After extracting feature values from images, pooling (or downsampling) layers are used to reduce the number of feature values while retaining the key differentiating features that have been extracted.

CONCLUSION – Train And Evaluate Deep Learning Models

In conclusion, this module offers an in-depth exploration of the essential principles of deep learning, equipping you with the expertise to create robust deep neural network models using PyTorch and TensorFlow. You will gain practical experience in building convolutional neural networks for image classification tasks, enhancing your understanding of their application in real-world scenarios. By completing this module, you will be well-prepared to leverage these cutting-edge technologies in your future projects and research endeavors, significantly advancing your skills in the field of deep learning.

Previous Module
Weekly Breakdown

Quiztudy Top Courses

Popular in Coursera

Liking our content? Then, don’t forget to ad us to your BOOKMARKS so you can find us easily!

Expanded Thumbnail Promo1

Mood Zone for Studying & Relaxing