Intro to Machine Learning

One answer per question, one attempt per quiz — you cannot retake it.

Question 1 of 5

What lesson about artificial intelligence does the conspect draw from the ancient Greek myth of Talos?

The myth suggests building mechanical automata was beyond ancient technology.Speech synthesis turned out to be harder than speech recognition.Automatically recognizing ships proved harder than throwing projectiles.The myth shows that AI was conceived only in modern times.

Question 2 of 5

Why did the Turing test remain a challenging benchmark for AI for many decades while other benchmarks were dismissed after being solved?

Because it requires a computer to stay in character during long conversations.Because it relies on free-form natural language, which requires broad knowledge.Because it was proposed by Alan Turing, giving it historical prestige.Because it uses probability theory to assess indistinguishability.

Question 3 of 5

According to Mitchell's definition, what must a computer program do to be considered to learn?

It must use neural networks and deep learning to improve its performance.It must get better at a task with experience, as gauged by a metric.It must generalize to new, unseen examples without overfitting.It must minimize a predefined loss function on the training data.

Question 4 of 5

What probability distribution is modelled in supervised learning, according to the conspect?

The joint probability distribution of both inputs and outputs, p(x,y).The conditional distribution of the output given the input, p(y|x).The marginal probability distribution of the input data, p(x).The posterior probability distribution of parameters given data, p(θ|D).

Question 5 of 5

What is the primary computational advantage of using a conjugate prior in Bayesian inference?

It always leads to a uniform posterior distribution.It allows updating hyperparameters instead of computing new integrals.It eliminates the need for a prior altogether.It guarantees that the maximum likelihood estimate equals the MAP estimate.

0 / 5 answered

Generated from lecture recordings by the autosummary pipeline.