Connectionist Neuron

Question 1

Basic elements of the neural model

Answer 1

1. A set of synapses, or connecting links, each of which is characterized by a weight or strength of its own. Specifically, a signal x_j at the input of synapse j connected to neuron k is multiplied by the synaptic weight w_kj
2. An adder for summing the input signals,weighted by the respective synaptic strengths of the neuron
3. An activation function for limiting the amplitude of the output of a neuron

Question 2

Activation function

Answer 2

a mathematical function which theoretically models the neuron’s output for each possible input

Question 3

Typical activation functions

Answer 3

1. Threshold or Heaviside function
2. Rectified linear unit
3. Sigmoid functions: Logistic function (β/4 - inflection point, values between 0 and 1, the function is differentiable), and hyperbolic tangent function (β - the inflection point, values between -1 and 1)

Question 4

Features

Answer 4

they characterize the essential information content of an input data set