Computational Intelligence, SS08
2 VO 442.070 + 1 RU 708.070 last updated:
General
Course Notes (Skriptum)
Online Tutorials
Introduction to Matlab
Neural Network Toolbox
OCR with ANNs
Adaptive Filters
VC dimension
Gaussian Statistics
PCA, ICA, Blind Source Separation
Hidden Markov Models
Mixtures of Gaussians
Automatic Speech Recognition
Practical Course Slides
Homework
Exams
Animated Algorithms
Interactive Tests
Key Definitions
Downloads
Literature and Links
News
mailto:webmaster
... FIR1
finite impulse response
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
... vector2
$ \nabla_{\mathbf{c}}$ is the `nabla' differential operator with respect to the vector $ \mathbf{c}$: $ \nabla_{\mathbf{c}} = \left[\frac{\partial }{\partial c_1}, \frac{\partial }{\partial c_2}, \ldots, \frac{\partial }{\partial c_d}\right]^{\mathsf T}$.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
... power3
The dependence of the stability bound on the signal power is exploited in the normalized LMS algorithm by normalizing the step-size according to the signal power: $ \mathbf{c}[n+1] = \mathbf{c}[n]+ \frac{\mu}{\epsilon+\Vert\mathbf{x}[n]\Vert^2} \, e^{\ast}[n] \, \mathbf{x}[n]$, with a small positive constant $ \epsilon$.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
... ADPCM4
adaptive differential pulse-code modulation
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.