Implement a multi-head attention mechanism. **Example:** For input [[1,2],[3,4]] and [[5,6],[7,8]], the output should be a weighted sum of the input values. **Constraints:** Use NumPy for efficient computation.
Test Cases
Test Case 1
Input:
[[1,2],[3,4]] [[5,6],[7,8]] [[9,10],[11,12]]Expected:
[[2.5,3.5],[6.5,7.5]]Test Case 2
Input:
[[1,1],[1,1]] [[1,1],[1,1]] [[1,1],[1,1]]Expected:
[[1.0,1.0],[1.0,1.0]]+ 3 hidden test cases