Deck 7: Neural Network Models and Deep Learning

ملء الشاشة (f)
exit full mode
سؤال
Axons, dendrites, and synapses are studied by what discipline, which is the inspiration for artificial neural networks? ___________________.
استخدم زر المسافة أو
up arrow
down arrow
لقلب البطاقة.
سؤال
Neural networks may be represented by an equation or instruction set.
سؤال
Unlike linear regression, neural networks can handle nonlinearities and interaction effects even when these are not explicit input variables.
سؤال
It is impossible to assess the relative importance of input variables in neural networks, which are a "black box".
سؤال
Cross-validation of a neural network (or other) model requires …

A) One or more test subsets
B) One or more hold-out subsets
C) One or more validation subsets
D) All of the above
سؤال
What is UNTRUE of hidden layers of neurons in a neural network model?

A) Depending on the software used, there may be more than one hidden layer.
B) It is possible to design a neural network with direct connections from the input to the output layer, skipping the hidden layer.
C) The more neurons in hidden layers, the better the resulting model fit.
D) Activation rules govern the firing of neurons.
سؤال
Explain "gradient descent" and what it does in a neural network algorithm.
سؤال
What makes a neural network model "supervised"?

A) input data in the test set includes the correct output values
B) input data in the training set includes the correct output values
C) input data in the test set includes the correct input values
D) input data in the training set includes the correct input values
سؤال
Which is possible with the "caret" package?

A) Running a nnet model
B) Running a neuralnet model
C) Both A and B
D) Neither A nor B
سؤال
Which package supports the Olden method of assessing the relative importance of predictors in a neural network model?

A) NeuralNetTools
B) neuralnet
C) nnet
D) caret
سؤال
What was a "violin plot" used for in Chapter 7, for the "iris" example?

A) to estimate variable importance
B) to obtain graphical insight into how separable the three classes of Species are on the four predictor variables.
C) to visualize the results of a neuralnet model
D) to visualize the results on a nnet model
سؤال
Neural networks may achieve better results if data are normalized or scaled.
سؤال
If data are normalized or scaled, which model performance metric will NOT change?

A) MSE
B) RMSE
C) R-squared
D) All of the above will change
E) None of the above will change
سؤال
The plotnet command is from which R package?

A) nnet
B) neuralnet
C) caret
D) NeuralNetTools
سؤال
What is NOT an advantage of running a neural model under caret?

A) optimization of all parameters is built in
B) tuning of some parameters is built in
C) cross-validation is built in
D) All of the above are advantages
سؤال
Which package brings to R some of the functionality of the Python environment, which is often preferred for large-scale neural network analysis?

A) bigdata
B) mlr3keras
C) caret
D) neuralnet
فتح الحزمة
قم بالتسجيل لفتح البطاقات في هذه المجموعة!
Unlock Deck
Unlock Deck
1/16
auto play flashcards
العب
simple tutorial
ملء الشاشة (f)
exit full mode
Deck 7: Neural Network Models and Deep Learning
1
Axons, dendrites, and synapses are studied by what discipline, which is the inspiration for artificial neural networks? ___________________.
Neurobiology.
In neurobiology, dendrites in neural networks collect signals which are fed to neurons. Neurons process a signal by sending a spike of electrical current along an axon, discharging at a synapse connected to other neurons, which in turn are excited or inhibited as a result.
2
Neural networks may be represented by an equation or instruction set.
False
Where ordinary statistical procedures are based on instruction sets (programs), ANNs are not. Instead ANNs pass data through multiple intermediary digital processing entities (neurons) on the way to output entities (neurons in the terminal layer). Intermediary neurons "learn" through shifting patterns of weights based on input signals. Shifting weights reflect better or worse predictions or classifications at the terminal output layer. In ANNs, no "solution" or "answer" is ever stored at a particular computer memory address. Rather, the solution takes the form of weighted connections along linkages from the input layer through one or more processing layers to an output layer of neurons.
3
Unlike linear regression, neural networks can handle nonlinearities and interaction effects even when these are not explicit input variables.
True
ANNs automatically handle nonlinearities and interaction effects in the data. Put another way, it is not necessary that causal dynamics in the field be well-enough understood that nonlinearity and interactions can be identified and explicitly incorporated in the model, as traditional statistical methods would require.
4
It is impossible to assess the relative importance of input variables in neural networks, which are a "black box".
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
5
Cross-validation of a neural network (or other) model requires …

A) One or more test subsets
B) One or more hold-out subsets
C) One or more validation subsets
D) All of the above
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
6
What is UNTRUE of hidden layers of neurons in a neural network model?

A) Depending on the software used, there may be more than one hidden layer.
B) It is possible to design a neural network with direct connections from the input to the output layer, skipping the hidden layer.
C) The more neurons in hidden layers, the better the resulting model fit.
D) Activation rules govern the firing of neurons.
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
7
Explain "gradient descent" and what it does in a neural network algorithm.
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
8
What makes a neural network model "supervised"?

A) input data in the test set includes the correct output values
B) input data in the training set includes the correct output values
C) input data in the test set includes the correct input values
D) input data in the training set includes the correct input values
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
9
Which is possible with the "caret" package?

A) Running a nnet model
B) Running a neuralnet model
C) Both A and B
D) Neither A nor B
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
10
Which package supports the Olden method of assessing the relative importance of predictors in a neural network model?

A) NeuralNetTools
B) neuralnet
C) nnet
D) caret
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
11
What was a "violin plot" used for in Chapter 7, for the "iris" example?

A) to estimate variable importance
B) to obtain graphical insight into how separable the three classes of Species are on the four predictor variables.
C) to visualize the results of a neuralnet model
D) to visualize the results on a nnet model
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
12
Neural networks may achieve better results if data are normalized or scaled.
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
13
If data are normalized or scaled, which model performance metric will NOT change?

A) MSE
B) RMSE
C) R-squared
D) All of the above will change
E) None of the above will change
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
14
The plotnet command is from which R package?

A) nnet
B) neuralnet
C) caret
D) NeuralNetTools
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
15
What is NOT an advantage of running a neural model under caret?

A) optimization of all parameters is built in
B) tuning of some parameters is built in
C) cross-validation is built in
D) All of the above are advantages
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
16
Which package brings to R some of the functionality of the Python environment, which is often preferred for large-scale neural network analysis?

A) bigdata
B) mlr3keras
C) caret
D) neuralnet
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.
فتح الحزمة
k this deck
locked card icon
فتح الحزمة
افتح القفل للوصول البطاقات البالغ عددها 16 في هذه المجموعة.