You must login before you can run this tool.
Trains a single sigmoidal unit using the delta rule to estimate posterior target probability given sensory input of two modalities (i.e., visual and auditory)
FIGURE 9.11 depicts a single, sigmoidal unit used to simulate a bisensory neuron in the superior colliculus. The unit y receives inputs X1 and x2 and a bias b. The weight matrix V is a row vector containing the weights of the three connections to y from x1, x2, and b. The unit computes the weighted sum of its inputs and passes the result through the sigmoidal squashing function (see Chapter 6). Inputs x1 and x2 could represent visual and auditory inputs, respectively, and the bias could represent constant influences on the firing rate of the collicular neuron.
Cite this work
Researchers should cite this work as follows: