Assignment #1

Question 1

Which of the following is not one of the key branches of machine learning?
  A. Reinforcement Learning
  B. Supervised Learning
  C. Deductive Learning
  D. Unsupervised Learning

Answer 1

C. Deductive Learning

Question 2

According to the article, as a result of advances in machine learning, systems can now outperform humans at all tasks.
True
False

Answer 2

False

Question 3

The famous computing test in which a machine might be called intelligent, if its responses to questions could convince a person that it was human, is known as the ______ test.

Answer 3

Turing

Question 4

In contrast to traditional programming approaches which rely on hard-coded rules, machine learning systems are assigned a \_\_\_\_\_\_ and given a large amount of \_\_\_\_\_\_\_ to use as examples of how the \_\_\_\_\_\_ can be accomplished.
  A. goal, instructions, goal
  B. task, data, task
  C. mission, simulations, mission
  D. task, examples, learning

Answer 4

B. task, data, task

Question 5

Both online and offline learning systems are trained and tested in an offline setting before deployment.
True
False

Answer 5

True

Question 6

While the underlying principles of machine learning are not new, recent advances in algorithmic techniques coupled with an increase in ___________ and _________ have resulted in increased accuracy and reliability of machine learning.
A. microprocessors, connected devices
B. computing power, available data
C. connected devices, online users
D. computing horsepower, artificial intelligence

Answer 6

B. computing power, available data

Question 7

The article draws a distinction between robots and what it calls 'bots' in that, robots are \_\_\_\_\_\_\_\_\_ agents, while 'bots' are \_\_\_\_\_\_\_\_ agents.
  A. sensory, automata
  B. physical, virtual
  C. intelligent, autonomous
  D. living, autonomous

Answer 7

B. physical, virtual

Question 8

In 2016, Google DeepMind's AlphaGo system made use of \_\_\_\_\_\_\_\_\_ learning to further improve it's ability to win at the game of Go.
  A. stochastic
  B. reinforcement
  C. unsupervised
  D. supervised

Answer 8

B. reinforcement

Question 9

Which of these is not a limitation of the existing approaches to machine learning?
A. Machine learning systems are not able to easily transfer ideas from one problem domain to another.
B. Machine learning systems tend to fail in a brittle manner.
C. Machine learning systems often cannot handle the large amounts of data available to them.
D. Human intent is complex and sometimes difficult to understand.

Answer 9

C. Machine learning systems often cannot handle the large amounts of data available to them.

Question 10

Machine learning exists in the cross-roads between data science, statistics and computer science.
True
False

Answer 10

True

Question 11

The machine learning approach in which an agent learns to identify strategies that minimize negative consequences while maximizing its reward is known as ________ learning.

Answer 11

reinforcement

Question 12

In the 18th century, English statistician, philosopher and Presbyterian minister, Thomas Bayes, developed a mathematical theorem for probability which is still foundational in modern day machine learning. What is this theorem called?
  A. Naive Bayes
  B. Probabilistic Theorem
  C. Bayes Theorem
  D. Bayesian Stochastics

Answer 12

C. Bayes Theorem