Welcome!
In 2000, the Signal Processing and Speech Communication Laboratory (SPSC Lab) of Graz University of Technology (TU Graz) was founded as a research and education center in nonlinear signal processing and computational intelligence, algorithm engineering, as well as circuits & systems modeling and design. It covers applications in wireless communications, speech/audio communication, and telecommunications.
If you want to learn more about Signal Processing, click: What is Signal Processing?
The Research of SPSC Lab addresses fundamental and applied research problems in five scientific areas:
- Audio and Acoustics
- Intelligent Systems
- Nonlinear Signal Processing
- Speech Communication
- Wireless Communications
Profiles
Result of the Month
Geometric and Information-Theoretic Compression in Stochastic Neural Networks
There has been a long-standing discussion whether information-theoretic compression in latent representations leads to improved generalization performance. While intuitive—compressed representations do not contain irrelevant input information on which the remaining part of a neural network can overfit—there is now substantial evidence that information-theoretic compression is not necessary for good generalization. Indeed, since many information estimators inherently capture geometric properties of the latent representations, geometric compression (i.e., clustering) has recently been proposed as an explanation of generalization.
In this paper, we investigate the interplay between information-theoretic compression, clustering, and generalization performance in stochastic neural networks. Considering both adaptive additive and fixed multiplicative noise at each neuron output, we show that the connection between these three concepts is more nuanced than initially believed.
Read the full article.Contact: Bernhard Geiger