# Quiz with answers — How a model learns from examples ### Question 1 Solve the worked-case variant: Replace input 2 with 2.4 while keeping weight 0.4 and target 1. Predict whether error increases or decreases, then recompute prediction and error before any update. - A. Prediction becomes 0.4×2.4=0.96 and target-minus-prediction error falls from 0.20 to 0.04. The update keeps the same direction but should be smaller because the model is already closer to target. - B. With weight 0.4, input 2, and target 1: prediction 0.8, error 0.2. With learning rate 0.1, the weight increases slightly. The lab shows the new prediction moving closer to 1. - C. This one-weight loop is a teaching model. Real models have many parameters, gradients, and optimizers. - D. The model applies whatever its current setting is: p = w × x. With w = 0.4 and x = 2 it proposes p = 0.8. That 0.8 is neither good nor bad in itself: it is the raw material for the comparison with the target 1. **Answer: A.** Prediction becomes 0.4×2.4=0.96 and target-minus-prediction error falls from 0.20 to 0.04. The update keeps the same direction but should be smaller because the model is already closer to target. The correct answer executes the requested change and gives a checkable result; the other texts do not close this calculation or trace. --- ### Question 2 Which causal order correctly connects the first three stages of “How a model learns from examples”? - A. Measure the error → The prediction → An example and a target - B. An example and a target → The prediction → Measure the error - C. The prediction → An example and a target → Measure the error - D. An example and a target → Measure the error → The prediction **Answer: B.** An example and a target → The prediction → Measure the error The chain follows the taught progression; reversing stages consumes a representation or state before it is produced. --- ### Question 3 If “Measure the error” is removed, which diagnostic method is defensible? - A. Also change the data to amplify the difference. - B. Observe only the final output and invent the cause. - C. Keep the same input, predict the first output that depends on “Measure the error,” then compare the before/after trace. - D. Conclude that the whole system fails before measuring. **Answer: C.** Keep the same input, predict the first output that depends on “Measure the error,” then compare the before/after trace. One intervention and a prior prediction make the delta attributable to the removed mechanism. --- ### Question 4 Which verdict respects this session’s validity boundary? - A. The mechanism guarantees accuracy, speed, and stability for every workload. - B. One successful example proves the whole architecture is superior. - C. The mechanism name alone is enough for a production choice. - D. This one-weight loop is a teaching model. Real models have many parameters, gradients, and optimizers. **Answer: D.** This one-weight loop is a teaching model. Real models have many parameters, gradients, and optimizers. The correct answer bounds the conclusion; the others turn a local relation into a global guarantee. --- ### Question 5 Which evidence best matches the stated status of “How a model learns from examples”? - A. Established mechanisms; numerical simplifications are pedagogical. - B. The route loads without an error. - C. Every learner opened the file. - D. The same result is assumed on every hardware target. **Answer: A.** Established mechanisms; numerical simplifications are pedagogical. Product or mechanism evidence must remain attributed and measured; availability and completion do not prove value. --- ### Question 6 When should a simpler baseline be preferred to “Repeat across many examples”? - A. Never: the newest mechanism wins by default. - B. When a controlled test shows equivalent quality with lower memory, latency, or complexity. - C. As soon as one memory metric falls, regardless of quality. - D. As soon as the diagram contains fewer components. **Answer: B.** When a controlled test shows equivalent quality with lower memory, latency, or complexity. The choice depends on a measured trade-off on the real workload, not novelty or one isolated metric. --- ### Question 7 A learner gets the right result but cannot explain “The prediction.” Which remediation is most useful? - A. Accept the answer because the final number is correct. - B. Provide the final result a second time. - C. Rebuild the first missing transformation, label its inputs and outputs, then test a neighboring case. - D. Change several variables and ask for an intuition. **Answer: C.** Rebuild the first missing transformation, label its inputs and outputs, then test a neighboring case. The remediation targets the first causal break and then requires transfer instead of rewarding a guessed result. --- ### Question 8 Which submission actually demonstrates the outcome “Run one simple numerical update.”? - A. A list of terms without causal relations. - B. A screenshot without values or interpretation. - C. A confident claim without a baseline or threshold. - D. A trace with starting data, transformations, observed result, boundary, and next experiment. **Answer: D.** A trace with starting data, transformations, observed result, boundary, and next experiment. The correct submission makes the reasoning reproducible and the verdict revisable by future measurement.