The diagram shown represents an artificial neural network.

Mark scheme

Marking points from the official mark scheme (Oct/Nov 2021). The mark or mark type is shown in brackets.

1. [1] Enables deep learning to take place
2. [1] Where the problem you are trying to solve has a higher level of complexity it requires more layers to solve
3. [1] To enable the neural network to learn and make decisions on its own
4. [1] To improve the accuracy of the result.
5. [1] Artificial neural networks are intended to replicate the way human brains work
6. [1] Weights / values are assigned for each connection between nodes
7. [1] The data are input at the input layer and are passed into the system
8. [1] They are analysed at each subsequent (hidden) layer where characteristics are extracted / outputs are calculated
9. [1] this process of training / learning is repeated many times to achieve optimum outputs // reinforcement learning takes place
10. [1] Decisions can be made without being specifically programmed
11. [1] The deep learning net will have created complex feature detectors
12. [1] The output layer provides the results
13. [1] Back propagation (of errors) will be used to correct any errors that have been made.
14. [1] Node B (from Home) (Line 3 in table)
15. [1] Node C (from Home) (Line 4 in table)
16. [1] Node B and Node E (from A) (Lines 5 and 6 in table)
17. [1] Node F and Node School (from E) (Lines 7 and 8 in table)
18. [1] Node School (from F) (Line 9 in table)
19. [1] Home A E F School
20. [5] Table values: Node Cost from Home node (g) Heuristic (h) Total (f = g + h) Home 0 14 14 A 1 10 11 B 5 7 12 C 4 9 13 B 1+3=4 7 11 E 1+6=7 3 10 F 7+1=8 3 11 School 7+5=12 0 12 School 8+3=11 0 11 Final Path: Home -> A -> E -> F -> School