In the neural network above, given the initial weights, the biases, and training inputs/outputs, calculate the output of node o1 using the forward pass algorithm. (10 points) 

If 60% of ML students pass the final and 45% of ML students pass both the final and the midterm. What percent of students who passed the final also passed the midterm? (5 points) 

Discuss the bias/variance trade-off. (10 points)

What is the goal of the SVM algorithm? (5 points)

Use the information in the table below to answer the following question:  Using the algorithm for information gain calculate the entropy for each (parent as well as child) attribute. (20 points) Color Size Shape Edible? Yellow Small Round Yes Yellow Small Round Yes Green Small Irregular Yes Green Large Irregular No Yellow Large Round No Yellow Small Round Yes Yellow Small Round Yes Yellow Small Round Yes Green Small Round No Yellow Large Round No Yellow Large Round No Yellow Large Round No Yellow Large Round No Yellow Large Round No Yellow Small Irregular Yes Yellow Large Irregular No

Team 10 discussed three insights from working with “Where I’m From” related to data, internal communications, and the pivot from the midpoint to the final deliverable. Describe in your own words your takeaways from their presentation, paying careful attention to the biggest assumption they made in their initial expectation about what the client would provide and what they did in the final deliverable to manage challenging communications with the client.

When you’re using scale/continuous variables, descriptive statistics summarize their distribution. The use of parametric tests compares group means for significance. 

The Three Interrogation Moves can be described as:  Move One is [move1] the Claim. Move Two is [move2] the Evidence. Move Three is [move3] the Implication.

Describe in your own words at least two core course concepts Team 8 (Power2Hydrogen) leveraged in their project from Marketing, Strategy, and the use of AI. Be specific! 

When you began probing your client to understand potential falsification of the issue trees you first constructed, what were the real client/customer constraints you had to pay attention to? Give your response, paying careful attention to any of the following that you ran into: Client constraints (time, customer access, limits on access) Bias (researcher, respondent, sampling)   The need to triangulate what you heard Evidence strength (limitations of what you can access) Challenges in survey design (what you elected to collect, and what you wished you had done)