This paper describes a simple method for significantly improving Tandem features used to train acoustic models for large-vocabulary speech recognition. The linear activations at ...
In this work, we propose a new grid conversion algorithm between the hexagonal lattice and the orthogonal (a.k.a. Cartesian) lattice. The conversion process, named H2O, is easy to...
Aiming at improving image segmentation and extending regular computer vision algorithms an image sensor, acquiring additional depth information is deployed. The novel Photonic Mix...
Frank Wallhoff, Martin Russ, Gerhard Rigoll, Johan...
Unlike mono-agent systems, multi-agent planing addresses the problem of resolving conflicts between individual and group interests. In this paper, we are using a Decentralized Ve...
This paper proposes novel hierarchical self-organizing associative memory architecture for machine learning. This memory architecture is characterized with sparse and local interco...