# Introduction to Deep Learning & Neural Networks with Keras Quiz Answers

### Introduction to Deep Learning & Neural Networks with Keras Week 01 Quiz Answers

#### Quiz: Introduction to Neural Networks and Deep Learning

Q1. Which of the following are applications of deep learning?

• Color Restoration in Greyscale Images
• Self-Driving Cars
• Automatic Machine Translation
• Automatic Handwriting Generation
• All of the Above

Q2. An artificial neural network can be composed of which of the following types of layers?

• Output Layer
• Hidden Layer
• Sparse Layer
• Input Layer
• Intermediate Layer

Q3. A artificial neuron is so powerful that it can perform complex tasks by simply performing a linear combination of its inputs.

• True
• False

Q4. Given below is a neural network with one neuron that takes two float numbers as inputs. • 0.2675

Q5. What is the value of z for the given x1 and x2 (Give your answer to three decimal places)\

The model in the previous question uses the sigmoid activation function. What is the output of the network?

• 0.566479056

### Introduction to Deep Learning & Neural Networks with Keras Week 02 Quiz Answers

#### Quiz: Artificial Neural Networks

Q1. The weights and biases in a neural network are optimized using:

• Activation Descent
• Activation Function
• Logistic Descent

Q2. For a cost function, J = \sum_{i=1}^{m}{(z_{i} – wx_{i} – b)^2} J=∑i=1m​(zi​−wxi​−b)2, that we would like to minimize, which of the following expressions represent updating the parameter, w w, using gradient descent?

• w \rightarrow w + b – \eta * \frac{\partial J}{\partial w} ww+bη∗∂wJ
• w \rightarrow w + \eta * \frac{\partial J}{\partial w} ww+η∗∂wJ
• w \rightarrow w – \eta * \frac{\partial J}{\partial w} wwη∗∂wJ
• w \rightarrow w – \eta * x\frac{\partial J}{\partial w} wwηxwJ
• w \rightarrow w – \eta * b\frac{\partial J}{\partial w} wwηbwJ

Q3. What type of activation function is this? • Binary Function
• Linear Function
• Sigmoid Function
• ReLU
• Hyperbolic Tangent Function
• Leaky ReLU

Q5. What type of activation function is this? • Binary Function
• Leaky ReLU
• Hyperbolic Tangent Function
• Sigmoid Function
• Linear Function
• ReLU

Q5. Softmax activation function is most commonly used in hidden layers?

• True
• False

### Introduction to Deep Learning & Neural Networks with Keras Week 03 Quiz Answers

#### Quiz: Keras and Deep Learning Libraries

Q1. Which ofthe following statements is correct?

• Among TensorFlow, PyTorch, and Keras, Keras is the most popular library and is mostly used in production of deep learning models.
• TensorFlow is the cousin of the Torch framework, which is in Lua, and supports machine learning algorithms running on GPUs in particular.
• PyTorch normally runs on top of a low-level library such as TensorFlow.
• Keras is a high-level API that facilitates fast development and quick prototyping of deep learning models.
• Keras and PyTorch are both supported by Google and are being actively used at Google for both research and production needs.

Q2. Both TensorFlow and PyTorch are high level APIs for building deep learning models. They provide limited control over the different nodes and layers in a network. If you are seeking more control over a network, then Keras is the right library.

• True
• False

Q3. There are three model classes in the Keras library, the Sequential model, the Dense model, and the Model class used with the functional API.

• True
• False

Q4. Which of the following codes creates the followig neural network using the Keras library? Q5. If a model can be saved using the Keras library, which of following methods is the correct method to do so?

• model.model_save()
• model.save()
• model.save_model()
• model.pickle()
• You cannot save a model with the Keras library

### Introduction to Deep Learning & Neural Networks with Keras Week 04 Quiz Answers

#### Quiz: Deep Learning Models

Q1. Why is the convolutional layer important in convolutional neural networks?

• Because a convolutional layer would make the model overfit the training data so that it generalizes better
• Because convolutional neural networks are unsupervised deep learning models and therefore, a convolutional layer helps the model better fit the data
• Because if we do not use a convolutional layer, we will end up with a massive number of parameters that will need to be optimized and it will be super computationally expensive
• Because convolutional neural networks take flattened images as input and therefore the convolutional layer helps the model regenerate the input images
• None of the above

Q2. The following is a typical architecture of a convolutional neural network. • True
• False

Q3. For unsupervised learning, which of the following deep neural networks would you choose? Select all that apply

• Convolutional Neural Netwroks
• Restricted Boltzmann Machines
• Autoencoders
• Long Short Term Memory Networks
• Recurrent Neural Networks

Q4. Recurrent Neural Networks are networks with loops, that don’t just take a new input at a time, but also take as input the output from the data point at the previous instance.

• True
• False

Q5. Which of the following statements is correct?

• A convolutional neural network is an unsupervised neural network model that uses backpropagation by setting the target variable to be the same as the input
• An autoencoder is an unsupervised neural network model that uses backpropagation by setting the target variable to be the same as the input
• An autoencoder consists of a series of convolutional, ReLU, and pooling layers, as well as a number of fully connected layers
• Just like conventional neural networks, a convolutional neural network takes (n x 1) vectors as input
• Recurrent neural networks are best for solving problems related to image recognition, object detection, and other computer vision applications
##### Get all Course Quiz Answers of IBM AI Engineering Professional Certificate

Machine Learning with Python Coursera Quiz Answers

Introduction to Deep Learning & Neural Networks with Keras Quiz Answers

Introduction to Computer Vision and Image Processing Quiz Answers

Deep Neural Networks with PyTorch Coursera Quiz Answers

Building Deep Learning Models with TensorFlow Coursera Quiz Answers

AI Capstone Project with Deep Learning Coursera Quiz Answers ##### Team Networking Funda

Welcome to the official Author Page of Team Networking Funda! Here, we are dedicated to unraveling the intricate world of networking, connectivity, and team dynamics. Our mission is to provide you with insightful, actionable advice and solutions that will help you build strong connections, foster collaboration, and achieve success in all aspects of your professional life.

🌐 Networking Insights: Dive into the art of networking with us, as we explore strategies, tips, and real-world examples that can elevate your networking game. Whether you're a seasoned pro or just starting, we have valuable insights to offer.

🤝 Team Synergy: Discover the secrets to creating high-performing teams. We delve into team dynamics, leadership, and communication to help you unlock the full potential of your team and achieve outstanding results.

🚀 Professional Growth: Explore the tools and techniques that can accelerate your professional growth. From career development to personal branding, we're here to guide you toward achieving your goals.

🌟 Success Stories: Be inspired by success stories, case studies, and interviews with experts who have mastered the art of networking and teamwork. Learn from their experiences and apply their insights to your journey.

💬 Engage and Connect: Join the conversation, leave comments, and share your own networking and team-building experiences. Together, we can create a vibrant community of like-minded professionals dedicated to growth and success.

Stay tuned for a wealth of resources that will empower you to excel in your professional life. We're here to provide you with the knowledge and tools you need to thrive in today's interconnected world.

We are Team Networking Funda, a group of passionate authors and networking enthusiasts committed to sharing our expertise and experiences in the world of networking and team building. With backgrounds in [Your Background or Expertise], we bring a diverse range of perspectives and insights to help you navigate the challenges and opportunities of professional networking and teamwork.

error: Content is protected !!