WorksheetsIntro to Neural Networks Review
Total questions: 29
Worksheet time: 16mins
Which of these are reasons for Deep Learning recently taking off? (Check the three options that apply.)
We have access to a lot more computational power.
Neural Networks are a brand new field.
We have access to a lot more data.
Deep learning has resulted in significant improvements in important applications such as online advertising, speech recognition, and image recognition.
2. The job of which of the following layer is to acquire data and feed it to the neural network?
Input
Hidden
Output
Last
Which is the correct structure of a Neural Network?
Output, Hidden Layer, Input
Hidden Layer, Input, Output
Input, Hidden Layer, Output
How many hidden layers have the following Neural network
4
5
6
7
Which of the following statements is true?
The deeper layers of a neural network are typically computing more complex features of the input than the earlier layers.
The earlier layers of a neural network are typically computing more complex features of the input than the deeper layers.
What allows a neural network to learn non-linearly separable problems?
Having more than one neuron
Having more than one layer
Having enough training data
Training for a long time
What does a neuron, the basic unit of a neural network, do?
Performs a multiplication on its inputs
Computes a weighted sum of its inputs, and outputs a nonlinear function of this sum
Computes the maximum of its inputs, and outputs this maximum
Generates a random number between 0 and 1, and outputs this number
If a neural network is overfitting, what strategies would help? Select all that apply.
Introducing dropout
Reducing the number of layers in the model
Increasing the learning rate
Increasing the size of the training data
The most suitable activation function for hidden layer
Sigmoid
ReLu
Softmax
tanh
Which one of these plots represents a ReLU activation function?
Given the neural network inputs and weights and assuming no bias and linear activation, what would the output be?
3
-2
5
-4
Given the neural network inputs and weights and assuming no bias and linear activation, what would the output be?
7
-11
18
5
Backpropagation calculates the ____ and propagates it back to earlier layers.
value
error
data
Control the strength of the connections between the neurons
Artificial Intelligence
Bias
Neuron
Weight
Find the ideal choice of activation function for output layer for predicting multiple classes
Softmax
Relu
Sigmoid
Tanh
Constant which helps the model in a way that it can fit best for the given data
Weight
Neuron
Bias
Layers
Collection of 'neurons' operating together at a specific depth within a neural network
Bias
Weight
Neuron
Layers
When an ENTIRE dataset is passed forward and backward through the neural network only ONCE
One epoch
One batch
One iteration
What if we would like to have prediction output (binary classification) represented by probability, which activation function is the best choice?
tanh
ReLu
Sigmoid
Linear
Which is the best output configuration for a model tasked with classifying a person's mood, e.g. angry, happy, sad etc. by the tone of their voice?
One neuron with sigmoid
Multiple neurons with softmax
One neuron with linear output
None of these
Deep learning algorithm for sequential problem
CNN
ANN
DBN
RNN
The number of batches needed to complete one epoch
Iterations
Epochs
Batch
The activation of each neuron in a layer is determined by the __________ of the activations of all the neurons in the previous layer.
weighted sum
sum
level
What is gradient descent?
a way to determine how well the machine learning model has performed given the different values of each parameter
method to increase the speed of Neural Network operation
an optimization algorithm used to find the values of parameters (coefficients) of a function (f) that minimizes a cost function (cost)
different name for activation function
What is activation function?
a way to determine how well the machine learning model has performed given the different values of each parameter
an optimization algorithm used to find the values of parameters (coefficients) of a function (f) that minimizes a cost function (cost)
function describes how computationally expensive is a neural network
function used to enable Neural Network to solve non-linear problems
What activation function is it?
sigmoid
tanh
ReLU
ELU
What activation function is it?
sigmoid
tanh
ReLU
ELU
What activation function is it?
sigmoid
tanh
ReLU
ELU
What did you think of Quizizz?
Eh, not my thing.
It was okay!
Great!
