# Quiz with answers — Linear attention and fixed-size matrix memory ### Question 1 Solve the worked-case variant: For write k=[1,0], replace v=[2,3] with v=[2.4,3]. Recompute S and then read with q=[1,0]. - A. S becomes [[2.4,3],[0,0]] and qᵀS reads [2.4,3]. Only the first coordinate of the written value changes; selection through k and q is unchanged. - B. With zero S, k=[1,0] and v=[2,3], the write gives [[2,3],[0,0]]. Query q=[1,0] reads [2,3]. Trying to add a length-3 key [1,0,2] also reveals why shape checks are mandatory. - C. Fixed memory means neither perfect memory nor infinite context: capacity and interference remain bounded. - D. The dot product compresses alignment into one number: q·k = Σqᵢkᵢ. Here q=[1,0] against k=[1,0] gives 1 (aligned); against k=[0,1] it gives 0 (orthogonal). That is the addressing mechanism: strong = relevant, zero = ignored. **Answer: A.** S becomes [[2.4,3],[0,0]] and qᵀS reads [2.4,3]. Only the first coordinate of the written value changes; selection through k and q is unchanged. 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 “Linear attention and fixed-size matrix memory”? - A. Outer product → Dot product → Matrix foundations - B. Dot product → Matrix foundations → Outer product - C. Matrix foundations → Dot product → Outer product - D. Matrix foundations → Outer product → Dot product **Answer: C.** Matrix foundations → Dot product → Outer product The chain follows the taught progression; reversing stages consumes a representation or state before it is produced. --- ### Question 3 If “Outer product” is removed, which diagnostic method is defensible? - A. Also change the data to amplify the difference. - B. Keep the same input, predict the first output that depends on “Outer product,” then compare the before/after trace. - C. Observe only the final output and invent the cause. - D. Conclude that the whole system fails before measuring. **Answer: B.** Keep the same input, predict the first output that depends on “Outer product,” 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. Fixed memory means neither perfect memory nor infinite context: capacity and interference remain bounded. **Answer: D.** Fixed memory means neither perfect memory nor infinite context: capacity and interference remain bounded. 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 “Linear attention and fixed-size matrix memory”? - 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 “Fixed memory”? - A. Never: the newest mechanism wins by default. - B. As soon as one memory metric falls, regardless of quality. - C. When a controlled test shows equivalent quality with lower memory, latency, or complexity. - D. As soon as the diagram contains fewer components. **Answer: C.** 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 “Dot product.” Which remediation is most useful? - A. Accept the answer because the final number is correct. - B. Rebuild the first missing transformation, label its inputs and outputs, then test a neighboring case. - C. Provide the final result a second time. - D. Change several variables and ask for an intuition. **Answer: B.** 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 “Diagnose interference.”? - 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.