# Sequences, Time Series and Prediction Quiz Answers

## Sequences, Time Series and Prediction Week 01 Quiz Answers

### Sequences, Time Series and Prediction

Q1: What is an example of a Univariate time series?

• Hour by hour weather
• Baseball scores
• Fashion items
• Hour by hour temperature

Q2: What is an example of a Multivariate time series?

• Baseball scores
• Hour by hour temperature
• Hour by hour weather
• Fashion items

Q3: What is imputed data?

• A good prediction of future data
• A bad prediction of future data
• A projection of unknown (usually past or missing) data
• Data that has been withheld for various reasons

Q4: A sound wave is a good example of time series data

• False
• True

Q5: What is Seasonality?

• Data that is only available at certain times of the year
• A regular change in shape of the data
• Weather data
• Data aligning to the 4 seasons of the calendar

Q 6: What is a trend?

• An overall consistent flat direction for data
• An overall consistent downward direction for data
• An overall consistent upward direction for data
• An overall direction for data regardless of direction

Q7: In the context of time series, what is noise?

• Sound waves forming a time series
• Data that doesn’t have a trend
• Data that doesn’t have seasonality
• Unpredictable changes in time series data

Q8: What is autocorrelation?

• Data that follows a predictable shape, even if the scale is different
• Data that doesn’t have noise
• Data that automatically lines up in trends
• Data that automatically lines up seasonally

Q9: What is a non-stationary time series?

• One that has a constructive event forming trend and seasonality
• One that has a disruptive event breaking trend and seasonality
• One that is consistent across all seasons
• One that moves seasonally

## Sequences, Time Series and Prediction Week 02 Quiz Answers

Q1: What is a windowed dataset?

• A consistent set of subsets of a time series
• There’s no such thing
• The time series aligned to a fixed shape
• A fixed-size subset of a time series

Q2: What does ‘drop_remainder=true’ do?

• It ensures that the data is all the same shape
• It ensures that all data is used
• It ensures that all rows in the data window are the same length by cropping data
• It ensures that all rows in the data window are the same length by adding data

Q3: What’s the correct line of code to split an n column window into n-1 columns for features and 1 column for a label

• dataset = dataset.map(lambda window: (window[n-1], window[1]))
• dataset = dataset.map(lambda window: (window[:-1], window[-1:]))
• dataset = dataset.map(lambda window: (window[-1:], window[:-1]))
• dataset = dataset.map(lambda window: (window[n], window[1]))

Q4: What does MSE stand for?

• Mean Slight error
• Mean Squared error
• Mean Series error
• Mean Second error

Q5: What does MAE stand for?

• Mean Average Error
• Mean Absolute Error
• Mean Active Error

Q6: If time values are in time[], series values are in series[] and we want to split the series into training and validation at time 1000, what is the correct code?

time_train = time[:split_time]

x_train = series[:split_time]

time_valid = time[split_time:]

x_valid = series[split_time:]

time_train = time[split_time]

x_train = series[split_time]

time_valid = time[split_time:]

x_valid = series[split_time:]

time_train = time[:split_time]

x_train = series[:split_time]

time_valid = time[split_time]

x_valid = series[split_time]

time_train = time[split_time]

x_train = series[split_time]

time_valid = time[split_time]

x_valid = series[split_time]

Q7: If you want to inspect the learned parameters in a layer after training, what’s a good technique to use?

• Run the model with unit data and inspect the output for that layer
• Decompile the model and inspect the parameter set for that layer
• Assign a variable to the layer and add it to the model using that variable. Inspect its properties after training
• Iterate through the layers dataset of the model to find the layer you want

Q8: How do you set the learning rate of the SGD optimizer?

• Use the lr property
• You can’t set it
• Use the Rate property
• Use the RateOfLearning property

Q9: If you want to amend the learning rate of the optimizer on the fly, after each epoch, what do you do?

• Use a LearningRateScheduler and pass it as a parameter to a callback
• Callback to a custom function and change the SGD property
• Use a LearningRateScheduler object in the callbacks namespace and assign that to the callback
• You can’t set it

## Sequences, Time Series and Prediction Week 03 Quiz Answers

### Sequences, Time Series and Prediction

Q1: If X is the standard notation for the input to an RNN, what are the standard notations for the outputs?

• Y
• H
• Y(hat) and H
• H(hat) and Y

Q2: What is a sequence to vector if an RNN has 30 cells numbered 0 to 29

• The Y(hat) for the first cell
• The total Y(hat) for all cells
• The Y(hat) for the last cell
• The average Y(hat) for all 30 cells

Q3: What does a Lambda layer in a neural network do?

• Changes the shape of the input or output data
• There are no Lambda layers in a neural network
• Pauses training without a callback
• Allows you to execute arbitrary code while training

Q4: What does the axis parameter of tf.expand_dims do?

• Defines the dimension index to remove when you expand the tensor
• Defines the axis around which to expand the dimensions
• Defines if the tensor is X or Y
• Defines the dimension index at which you will expand the shape of the tensor

Q5: A new loss function was introduced in this module, named after a famous statistician. What is it called?

• Hubble loss
• Hawking loss
• Huber loss
• Hyatt loss

Q6: What’s the primary difference between a simple RNN and an LSTM

• LSTMs have a single output, RNNs have multiple
• LSTMs have multiple outputs, RNNs have a single one
• In addition to the H output, RNNs have a cell state that runs across all cells
• In addition to the H output, LSTMs have a cell state that runs across all cells

Q7: If you want to clear out all temporary variables that tensorflow might have from previous sessions, what code do you run?

• tf.cache.clear_session()
• tf.keras.backend.clear_session()
• tf.keras.clear_session
• tf.cache.backend.clear_session()

Q8: What happens if you define a neural network with these two layers?

tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),

tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),

tf.keras.layers.Dense(1),

• Your model will fail because you have the same number of cells in each LSTM
• Your model will fail because you need return_sequences=True after the first LSTM layer
• Your model will compile and run correctly
• Your model will fail because you need return_sequences=True after each LSTM layer

## Sequences, Time Series and Prediction Week 04 Quiz Answers

### Sequences, Time Series and Prediction

Q1: How do you add a 1 dimensional convolution to your model for predicting time series data?

• Use a 1DConvolution layer type
• Use a Conv1D layer type
• Use a Convolution1D layer type
• Use a 1DConv layer type

Q2: What’s the input shape for a univariate time series to a Conv1D?

• []
• [None, 1]
• [1]
• [1, None]

Q3: You used a sunspots dataset that was stored in CSV. What’s the name of the Python library used to read CSVs?

• CommaSeparatedValues
• PyFiles
• CSV
• PyCSV

Q4: If your CSV file has a header that you don’t want to read into your dataset, what do you execute before iterating through the file using a ‘reader’ object?

Q5: When you read a row from a reader and want to cast column 2 to another data type, for example, a float, what’s the correct syntax?

• You can’t. It needs to be read into a buffer and a new float instantiated from the buffer
• Convert.toFloat(row[2])
• float(row[2])

Q6: What was the sunspot seasonality?

• 11 years
• 11 or 22 years depending on who you ask
• 4 times a year
• 22 years

Q7: After studying this course, what neural network type do you think is best for predicting time series like our sunspots dataset?

• RNN / LSTM
• DNN
• Convolutions
• A combination of all of the above

Q8: Why is MAE a good analytic for measuring accuracy of predictions for time series?

• It punishes larger errors
• It biases towards small errors
• It only counts positive errors
• It doesn’t heavily punish larger errors like square errors do