Service accounts authenticate applications running on your virtual machine instances to other Google Cloud Platform services. For example, if you write an application that reads and writes files on Google Cloud Storage, it must first authenticate to the Google Cloud Storage API. At a minimum, service accounts used with Cloud Dataproc need permissions to read and write to Google Cloud Storage, and to write to Google Cloud Logging.
Reference: https://cloud.google.com/dataproc/docs/concepts/service-
accounts#important_notes

When query results are retrieved from a cached results table, you are not charged for the query. BigQuery caches query results for 24 hours, not 48 hours. Query results are not cached if you specify a destination table. A query's results are always cached except under certain conditions, such as if you specify a destination table.
Reference: https://cloud.google.com/bigquery/querying-data#query-caching

Traditional machine learning relies on shallow nets, composed of one input and one output layer, and at most one hidden layer in between. More than three layers (including input and output) qualifies as "deep" learning.
So deep is a strictly defined, technical term that means more than one hidden layer.
In deep-learning networks, each layer of nodes trains on a distinct set of features based on the previous layer's output. The further you advance into the neural net, the more complex the features your nodes can recognize, since they aggregate and recombine features from the previous layer.
A neural network with only one hidden layer would be unable to automatically recognize high-level features of faces, such as eyes, because it wouldn't be able to "build" these features using previous hidden layers that detect low-level features, such as lines.
Feature engineering is difficult to perform on raw image data.
K-means Clustering is an unsupervised learning method used to categorize unlabeled data.
Reference: https://deeplearning4j.org/neuralnet-overview