General objectives
The IMSE Neuromorphic group targets the development of brain inpsired artificial systems able to emulate the sensing and cognitive capabilities of biological beings.
The IMSE Neuromorphic group has focused on developing intelligent, high-speed, low power artificial vision systems. The group focuses mainly on event-driven (spiking) frame-free vision systems, developing sensing retinas for spatial or temporal contrast (such as DVS – Dynamic Vision Sensors), as well as event-driven convolution processors, which allow to assemble for example large scale spiking “Convolutional Neural Networks” for high speed object recognition. These chips and systems use AER (Address Event Representation) communication techniques.
Developed chips use analog, digital or mixed signal techniques, low current, and/or low power, as well as high speed communication techniques. The group has also developed event-based processor on digitally programmable devices as FPGAs, as well as multi-chip and hybrid chip-FPGA systems to scale up to higher complexity systems.
The group also works on algorithms and sensory processing for spiking information sensing, coding and processing. In particular, the group has proposed the implementation of on-line spike-timing-depent-plasticity learning circutis exploiting emergent nanoscale technologies or new devices like memristors (EU NABAB project , PNEUMA project and NEURAM3 project).
Specific objectives
The group has contibuted to the following specific areas:
- Artificial bioinspired asynchronous event driven vision sensors
- Asynchronous event driven convolution processors
- Modularly assembled event-based sensing and procsessing systems
- Learning with Spike-Timing-Dependent Plasticity
- Use of emerging nanodevices as adaptable learning synaptic devices
- Analog design of low power and/or low current circuits and blocks for neuromorphic systems
- Calibration techniques for analog computing circuits