| Date | May 2018 | Marks available | 2 | Reference code | 18M.2.HL.TZ0.8 |
| Level | HL | Paper | 2 | Time zone | no time zone |
| Command term | Calculate | Question number | 8 | Adapted from | N/A |
Question
Neural networks are often used to model the complex behaviour of systems. These networks must first be trained in order to establish a reliable model. One such method of training makes use of supervized learning algorithms.
Outline the basic steps involved in supervized learning algorithms.
The following block diagram illustrates a neural network used by a supervized learning algorithm to calculate a resulting value RES, for a given set of inputs.
The neural network in the block diagram contains 60 nodes in the input layer (block I), 36 nodes in the hidden layer (block H) and 6 nodes in the outermost layer (block O). The solid black arrows indicate that all nodes in one layer are feeding all nodes in the successive layer. In particular, the value RES is calculated by using all nodes in O.
Calculate the number of weights that the above neural network uses in producing a value for RES. Show the details of your calculation.
Markscheme
Award [4 max]:
Uses a (training) set of input data and known response values;
To compare the model's output with actual values from the past which will give an error in the estimate;
The model is then changed in order to minimize this error;
This process is iterated until a sufficiently accurate model is produced;
Which can then be used to make predictions/classifications;
Award [2 max].
Award [1] for evidence of multiplication between layers.
Award [1] for fully correct expression / answer.
60 * 36 + 36 * 6 + 6 * 1 = 2382
