Neural Turing Machines: Reading the Memory
Beginner
The problem, from first principles
A read in the NTM is a weighted sum of memory rows, so reading is differentiable and the controller learns where to look.
From theory to code
Implement ntm_read(w, memory), returning the weighted sum of memory rows.
Constraints
- Weights sum to one.
Hints
Hint 1
Multiply the weight vector by the memory matrix.
Keywords
research-paperssequence-modelsmemoryneural-computation
Python
Run your code to see results
No results yet
Run your code to check it against the examples, or submit to run every test.