Introduction
Over the last couple of decades the research of neuromorphic engineering community has focused on the understanding of low-level sensory processing and systems infrastructure. It is time to apply this knowledge and infrastructure to addressing higher-level problems in perception, cognition, and learning. The goal of this workgroup is to implement reservoir computation in hardware. Reservoir models, such as liquid-state machine (LSM), describe the activity of a random connected neural-network under the stimulation of time varying stimuli. By looking at the activity of the network it is possible to infer about the characteristics of the input stimuli. The ease of implementation of LSM make them an interesting tool for time-dependent sensory processing in hardware, even though the lack of a theoretical description of the parameter settings makes their realization a very hard task. The NCS group from the Institute of Neuroinformatics (Zurich) will ship a hardware setup of multi-neuron chips comprising arrays of integrate-and-fire neurons with dynamic synapses and spike-based learning algorithm for synaptic modifications. Participants will be provided with software tools (Python modules) for an easy design and realization of experiments of spiking neural-networks using hardware of the NCS group.
If you have interests in neuromorphic hardware and on how to use this hardware for building general purpose real-time cognitive systems this is the right place to start. Previous experience not required.
Informations
The neuromorphic setup of the NCS group
The Institute of Neuroinformatics in Zurich developed a hardware and software setup of neuromorphic chips implemented in VLSI technology communicating through Address Event Representation protocol (AER). Each chip comprises arrays of Leaky-Integrate-And-Fire neurons with dynamic synapses. A spike-based learning algorithm for synaptic weights modification is also implemented, as well as short-term depression and winner-take-all connectivity.
During the last two years the NCS group has put much effort in developing a complete package of Python modules to design, realize and analyze experiments using spiking neural-network in hardware. The pyNCS software provides tools for the creation of neural-networks with arbitrary topologies and automatic tuning of hardware parameters. Real-time interaction and monitoring of the activity of the network is possible. If you have a background in using software simulators of spiking neural-networks the transition to hardware should be fairly smooth (and hopefully exciting!).
More details about the hardware will be provided during the first week.
Reservoir-based computation
http://reservoir-computing.org/
Projects
A multi-layer, recurrent, excitatory-inhibitory neural network to project the input patterns into a high-dimensional space. Frèd please attach paper
An mdp hardware node
mdp stands for Modular Data Processing and the name is quite self-explaining for what it is designed for... In mdp specific functions applied to datasets, such as filters, are nodes of a flow-like structure. For example there is average node, the wta node and so on. The goal of the workgroup could be to implement a hardware reservoir node. The interaction between existing software-based signal-processing tools and spike-based hardware tools in real-time represents an interesting field itself. At least to us...
This part of the project was not developed
Prerequisites
Please refer to http://capocaccia.ethz.ch/capo/wiki/2011/classification11 for the hardware ans software requirements.
Knowledge requirements
Strong programming skills are suggested (Python).
Where to catch us
Our base location is at the bottom of the disco, right below the stage.
Results
Structure of the network
insert details here
Input-output test
insert details here
References
http://reservoir-computing.org/ [about reservoir computation]
http://capocaccia.ethz.ch/capo/wiki/2011/classification11 [about INI VLSI hardware]
