CS 451 Quiz 28
Intro to deep learning, NN basics, broadcasting
* Required
Email address
*
Your email
What example application is used in the video "What is a neural network"?
*
1 point
Cat detection
Housing price prediction
Handwritten digit recognition
What nonlinear activation function is used in the video "What is a neural network"?
*
1 point
sigmoid
tanh
ReLU
What's the difference between structured data and unstructured data?
*
1 point
In structured data, the input features are well defined (e.g. house size, # of bedrooms, zip code), while unstructured data has no clear features (e.g. audio, images, text)
Structured data has a differentiable loss function, while unstructured data does not
"Scale drives deep learning progress"  what does "scale" refer to?
*
1 point
More training data
Faster computers
More GPU cores
Better algorithms and faster computers have helped speed up what "cycle"?
*
1 point
Code > Test > Debug > Code
Train > Cross validation > Test > Train
Idea > Code > Experiment > Idea
Which of the following computations can be expressed with a computation graph? Check all that apply.
*
1 point
J = 3 ( a + b c )
y = x * ( x * ( x * a + b ) + c ) + d
A forward pass through a neural net
Required
To compute the derivative of the final output variable in a computation graph, we perform a
*
1 point
forward pass
backward pass
What does "broadcasting" mean?
*
1 point
Applying elementwise operations such as Matlab's .* and ./
Expanding a vector into a matrix of the appropriate size, duplicating the vector
It's another word for Python's "slicing" operation
Using Matlab / Octave notation, which of the following are legal operations when broadcasting is used? Check all that apply
*
1 point
[1 2; 3 4] .* [1 5]
[1 2; 3 4] + [1; 5]
[1 2; 3 4] + [1 2 3 4]
Required
If x is a "rank 1 array" whose shape is "(5,)", then x is equal to its transpose: x.T == x
*
1 point
True
False
Submit
This content is neither created nor endorsed by Google.
Report Abuse

Terms of Service
Forms