Reference no: EM133080010

Assessment Description

In this assignment, practical training issues are considered. There will be three basic issues addressed: the first describes things that need to be done prior to training a network, such as collecting and pre-processing data and selecting the network architecture; the second addresses network training itself; and the final considers post-training analysis. A case study is constructed for pattern recognition.

Assume a produce dealer has a warehouse that stores a variety of fruits and vegetables. When fruit is brought to the warehouse, various types of fruit may be mixed. The dealer wants a machine that will sort the fruit according to type. There is a conveyor belt on which the fruit is loaded. This conveyor belt passes through a set of sensors, which measure three properties of the fruit: shape, texture, and weight. These sensors are somewhat primitive. The shape sensor will output a 1 if the fruit is approximately round and a -1 if it is more elliptical. The texture sensor will output a 1 if the surface of the fruit is smooth and a -1 if it is rough. The weight sensor will output a 1 if the fruit is more than one pound and a -1 if it is less than one pound. The three sensor outputs will then be input to a neural network. The purpose of the network is to decide which kind of fruit is on the conveyor, so that the fruit can be directed to the correct storage bin. To make the problem even simpler, assume that there are only two kinds of fruit on the conveyor belt: banana and pineapple.

1. Select the network architecture and collect the pre-processing data.

2. Train the network.

3. Perform post-training and analysis.

4. Test the operation of your network by applying several different input patterns. Discuss the advantages and disadvantages of each input pattern.

5. How would you automate the training process using Python and libraries?

APA style is not required, but solid academic writing is expected.