Training data picking

Steps 5-7 are necessarily iterative and it should be expected that several modifications to both training data picking and/or selection of input data (attribute cubes) are required before a satisfactory result is achieved. In order to speed up the process, the workflow can be first run on a representative subvolume. After the training data have been picked, checked and parameters optimised, the neural network classification can then be run on the full volume of interest (Figure 3). 

Fig. 4. [Reproduced in colour in Plate 17 on page 433.] Picking of training data done by digitising portions of seismic patterns on seismic cross-sections. In this example six seismic facies or textures were defined, and several calibration samples used for each facies. Training data are picked on different sections within the zone of interest.

Once training data have been picked and checked, the neural network can be trained and classification be run on a subvolume for evaluation. After parameter optimization, the classification is run on the full volume of interest. 

Now that the SOM has been constructed and the weights vectors have been filled with random numbers, the next step is to feed in sample patterns. The SOM is shown every sample in the database, one at a time, so that it can learn the features that characterize the data. The precise order in which samples are presented is of no consequence, but the order of presentation is randomized at the start of each cycle to avoid the possibility that the map may learn something about the order in which samples appear as well as the features within the samples themselves. A sample pattern is picked at random and fed into the network unlike the patterns that are used to train a feedforward network, there is no target response, so the entire pattern is used as input to the SOM. 

When data size is not too large, one commonly prefers using the leave-one-out cross validation (Jackknife) method. This means that one data point is picked up for validation and the remaining data points are used for training. This process is repeated until each data point has been validated once. In other words, for a data consisted of n points, n validation models should be performed. 

Dai and MacBeth [1995] used an artificial neural network for automatic picking of local earthquake data. The network is trained on noise and P-wave segments. This method is also not applied to the raw signal directly, but to the modulus of a windowed segment of the signal. The output of the network consists of two values, which are parameters of a function that accentuates the difference between the actual output and ideal noise. The disadvantage of this approach is that it is time intensive. 

Employees need training to understand why personal protective equipment is necessary and how to use and maintain it properly. They must also understand its limitations. Personal protective equipment is designed for specific uses and is not always suitable in all situations. For example, no one type of glove or apron will protect employees against all solvents or physical hazards. To pick the appropriate glove or apron, employees should refer to recommendations on the material safety data sheets of the chemicals they are using or any manufacturers data sheets [3]. 

---