Python
What is an array?
An array is a collection of values or items
A survey taken from a small part of a population or group
A Sample
Machine learning is used to predict or conclude?
Predict
The neural network most commonly used for computer vision, which is designed to process data that come in the form of multiple arrays.
Convolutional Neural Network
How is human and animal learning unsupervised?
We learn by observation, not by being fed data.
In Python, a variable must be declared/created before it is assigned a value:
True or False?
False
A type of graph you would use a line of best fit for?
A scatter plot
In machine learning, programmers split their dataset into two parts: one for running the model and another for seeing how the model is performing?
What are the names of these two splits?
Train and test
A common method for training a neural network, encompassing these steps: using cost to compute gradients, updating weights?
Backpropagation
What is the difference between Intraclass Similarity an Interclass Dissimilarity?
Similar to the objects in the same cluster (intraclass similarity)
Dissimilar to the objects in other clusters (interclass dissimilarity)
number = input("Enter a number")
if number == 14:
print("hi")
else:
print("no")
What would be printed out if I ran this program with an input of 14?
It would give me "no" because I didn't convert number to an integer
What is the upper quartile of the following set of numbers: 1,4,6,7,8,9,11,14,16,18,20,24
17
What is the difference between a numpy array and an array?
numpy -> multidimensional
array -> 1 dimensional
What is forward propagation?
This term encompasses the following steps: using hypothesis function and weights to make predictions, compute cost
Procedures that could create layers of feature detector without requiring labeled data.
Unsupervised learning procedures.
Number_of_doughnuts = 4
If number_of_doghnuts > 4:
Number_of_doughnuts -= 3
Else:
Number_of_doughnuts +=9
What would this print if I typed print(Number_of_doughnuts)
13
A student says, "There was a very strong correlation of 1.22 between Sugar and Fat content." Explain the mistake made here.
Correlation is between -1 and +1.
Which model is commonly used for binary classification tasks?
Logistic regression
This approach to learning a function makes an initial guess, and adjusts the function based on how “wrong” it was.
Gradient Descent
What is learning rate?
Hyperparameter that controls how large of a "step" gradient descent takes
Why do we need function in python?
To bundle a set of instructions that you want to use repeatedly or that, because of their complexity, are better self-contained in a sub-program and called when needed.
From the in-class slides, and not Dr. McElwee's video lecture, what are the 5 Stages of a Data Science Life Cycle, in order?
Capture
Maintain
Process
Analyze
Communicate
What is softmax function?
This function outputs a vector which has elements that sum up to 1
Networks that are often used for tasks involving sequential inputs like speech and language
Recurrent neural networks
What is a loss function?
This function that takes in our estimated output values and true output values, and returns a number representing a difference between the two.