Radial-Basis Function Networks
Radial-Basis Function Networks
w1 < w3 < w2
NN 5 1
RBF
RBF ARCHITECTURE
x1
w1
ϕ1
x2
y
wm1
ϕ m1
xm
Rossella Cancelliere 1
NN 5
RBF
HIDDEN NEURON MODEL
x1
φσ( || x - t||)
x2 ϕσ
t is called center
σ is called spread
center and spread are parameters
xm
NN 5 3
RBF
HIDDEN NEURON MODEL
NN 5 4
Rossella Cancelliere 2
NN 5
RBF
Gaussian RBF φ
φ:
center
Large σ Small σ
NN 5 5
RBF
Interpolation with RBF
Rossella Cancelliere 3
NN 5
RBF
Types of φ
Micchelli’s theorem:
Let {xi }iN=1 be a set of distinct points in ℜ m
.Then the N-by-N interpolation
matrix Φ , whose ji-th element is ϕ ji (
= ϕ x j − xi ) is nonsingular.
(r2 + c2 ) 2
1
r =|| x − t ||
• Gaussian functions (most used):
r2
ϕ ( r ) = exp −
2 σ >0
2σ
NN 5 7
RBF
RBF network parameters
NN 5 8
Rossella Cancelliere 4
NN 5
RBF
Learning Algorithm 1
• Centers: are selected at random
– centers are chosen randomly from the training set
• Spreads: are chosen by normalization:
Maximum distance between any 2 centers d max
σ= =
number of centers m
1
(
ϕi x − ti
2
) = exp − dm
2
1 2
x − t i
max
NN 5 9
RBF
Learning Algorithm 1
NN 5 10
Rossella Cancelliere 5
NN 5
RBF
Learning Algorithm 1
NN 5 11
RBF
Learning Algorithm 1
Rossella Cancelliere 6
NN 5
RBF
Learning Algorithm 1: summary
NN 5 13
RBF
Learning Algorithm 2: Centers
• clustering algorithm for finding the centers
1 Initialization: tk(0) random k = 1, …, m1
2 Sampling: draw x from input space
3 Similarity matching: find index of center closer to x
Rossella Cancelliere 7
NN 5
NN 5 15
RBF
Learning Algorithm 3
• Apply the gradient descent method for finding
centers, spread and weights, by minimizing the
(instantaneous) squared error 1
E = ( y ( x ) − d )2
2
• Update for:
∂E
centers ∆t j = −ηt j
∂ tj
spread ∂E
∆σ j = −ησ j
∂σ j
weights ∂E
∆w ij = −ηij
∂w ij
NN 5 16
Rossella Cancelliere 8
NN 5
RBF
Comparison with multilayer NN
NN 5 17
RBF
Comparison with multilayer NN
• Architecture:
– RBF networks have one single hidden layer.
– FFNN networks may have more hidden layers.
• Neuron Model:
– In RBF the neuron model of the hidden neurons is different from the
one of the output nodes.
– Typically in FFNN hidden and output neurons share a common
neuron model.
– The hidden layer of RBF is non-linear, the output layer of RBF is
linear.
– Hidden and output layers of FFNN are usually non-linear.
NN 5 18
Rossella Cancelliere 9
NN 5
RBF
Comparison with multilayer NN
• Activation functions:
– The argument of activation function of each hidden neuron in
a RBF NN computes the Euclidean distance between input
vector and the center of that unit.
– The argument of the activation function of each hidden
neuron in a FFNN computes the inner product of input vector
and the synaptic weight vector of that neuron.
• Approximation:
– RBF NN using Gaussian functions construct local
approximations to non-linear I/O mapping.
– FF NN construct global approximations to non-linear I/O
mapping.
NN 5 19
Rossella Cancelliere 10