Basic blueprints: Design and proof-of-principle tests of fundamental architecture layouts for hierarchical neural system that can learn multi-scale sequence tasks.
Reservoir adaptation: Investigate mechanisms of adapting reservoirs, which are relevant for optimizing performance on the application benchmarks.
Spiking vs. non-spiking neurons, role of noise: Clarify the functional implications and different learning algorithms for spiking vs. non-spiking neurons and the role of noise.
Single-shot model extension, lifelong learning capability: Develop learning mechanisms which allow an existing cognitive architecture to become extended by new representational items in “single-shot” learning episodes to enable lifelong learning capabilities.
Working memory and grammatical processing: Extend the basic paradigm by mechanisms which function as an index-addressable working memory.
Interactive systems: Extend the adaptive capabilities of human-robot cooperative interaction systems by applying on-line and lifelong learning capabilities.
Integration of dynamical mechanisms: Integrate biologically mechanisms of learning, optimization, adaptation and stabilization into coherent architectures.
High performing, well formalized core engine: Collaborative development of a well formalized and high performing core engine, which will be made publicly accessible.
Comply to current FP6 unification initiatives: Ensure that the Engine integrates with the standards set in the FACETS FP6 IP, and integrate with other existing code.
Benchmark repository: Create a database with temporal, multi-scale benchmark data sets which can be used as an international touchstone for comparing algorithms.
Better automated speech recognition and handwriting recognition with reservoir computing:
Develop neural architectures for automated speech and handwriting recognition and efficient learning algorithms in these two target domains.
