机器学习考试代写 GR5241代写 EM Algorithm代写 Neural Network代写

2022/06/01机器学习代写考试助攻 EM Algorithm代写 Neural Network代写机器学习考试代写527

GR5241 – Final [80 pts]

机器学习考试代写 • Students must have their laptop camera on and microphone off during the exam. Everyone will be recorded for the exam duration,

Zoom based exam (same instructions on actual exam)

• Students must have their laptop camera on and microphone off during the exam. Everyone will be recorded for the exam duration, including submission.

• Position your laptop camera so that the TAs and instructor can clearly see you and your loose leaf paper.

• If a student does not have a printer, they can read the electronic copy from their computer screen.

• Students cannot use their computer for a calculator.

• No tablets or phones are allowed until the exam submission.

• Students must ask permission to use the restroom. Suspicious behavior will be flagged.

• Students will scan or take pictures of their completed final.

More details about the exam 机器学习考试代写

• The GR5241 final is open notes and closed book.

• All notes should be on looseleaf paper. This includes printed notes.

• Calculators are allowed (TI83, TI89, scientific… etc).

• A second computer, tablet, phone, or similar are not allowed.

• Students are not allowed to type on their keyboard, unless they want to ask a question to the instructor. In particular, browsing the internet is not allowed (no googling!).

• Students are not allowed to communicate with anyone about the final with the exception of the course TAs and instructor. (no emailing, WeChatting or similar).

• Cheating will result in a score of zero and will potentially be reported to the office of Student Conduct and Community Standards.

• Don’t cheat! Gabriel typically curves his final grades.

• Every student must write the following phrase on their cover page. Please fill in your printed name, signature and date. “I will not engage in academically dishonest activity for the STAT GR5241 final exam.”

Problem 1: EM Algorithm and Clustering [15 points] 机器学习考试代写

Consider flipping a biased coin several times until a head appears. Defifine the geometric random variable:

X = “number of trials until the first success (inclusive)”

In our case X represents the number of coin flips until the first heads and has probability mass function:

f(x|p) = p(1 − p)^{^x}^⁻¹ , x = 1, 2, . . . ,

where p = P(H) is the success probability of landing a heads.

Now consider an urn of K > 0 coins, each having its own success probability p₁, p₂, . . . , p_{_K}. Further, suppose that you randomly draw one of the K coins from the urn and flip that same coin until a head appears. Once you have recorded the number of trials that it took to show your first success, you replace the coin back into the urn and repeat the experiment numerous times. This new random variable X is now drawn from a mixture of geometric distributions:

Problem 4: Neural Network [10 points] 机器学习考试代写

Solve the following problems:

Consider the training case

X₁ = (1.27 0.41 −1.54), Y₁ = 0

4.i Classify the case X₁ based the above neural network. Show all details of your forward pass for full credit. Does the above neural network classify this case correctly?

4.ii Compute the contribution case i = 1 has on the total cost function, i.e., compute Q_{_i}. This should be very easy using your answer from part 4.i.

Problem 5: Classification Tree [5 points] 机器学习考试代写

Consider classifying the quality of white wine (Y = High or Y = Low) based on p = 11 continuous features.

For reference, the features are defined as:

X₁ = fixed acidity, X₂ = volatile acidity, X₃ = residual sugar, X₄ = citric acid, X₅ = chlorides, X₆ = free sulfur dioxide, X₇ = total sulfur dioxide, X₈ = density, X₉ = pH, X₁₀ = sulphates, X₁₁ = alcohol, Y = quality

Note that the feature names are not needed for this problem.

The classifier of interest is a decision tree. Based on the trained decision tree from Figure 1, classify the below test case. Hint: If TRUE left stem, If FALSE right stem.

x₁ = 6.5, x₂ = 0.16, x₃ = 0.34, x₄ = 1.4, x₅ = 0.029, x₆ = 29, x₇ = 133, x₈ = 0.99108, x₉ = 3.33, x₁₀ = 0.64, x₁₁ = 11.5

Problem 6: Penalty Terms [20 points]

Please Read: Students are not required to provide any formal derivations for problem parts 6.i-6.iv. Students should provide short written explanations.