We conduct interdisciplinary research at the interface between engineering, neuro-science, computer-science, and biology. We are interested in answering basic research questions that are related to the way neural circuits carry out computation, and at the same time in developing a new generation of computing technologies based on hybrid analog/digital neuromorphic circuits and CMOS VLSI technology.
Our funded projects are supported by the Swiss National Science Foundation, the EU FP7 program, as well as the European Space Agency.
We also work on running longer-term projects which offer possibilities for intern-ships, Master thesis and Semesterarbeit projects.
Funded projects currently under investigation
||Neuromorphic processors: event-based VLSI models of cortical circuits for brain-inspired computation (neuroP)
Brains are remarkable computing devices which clearly outperform conventional architectures in real-world tasks. Computational neuroscience has made tremendous progress in uncovering the key principles by which neural systems carry out computation, and ICTs have advanced to a point where it is possible to integrate almost as many transistors in a VLSI system as neurons in a brain. Yet, we are still unable to develop artificial neural systems with basic computing abilities able to parallel even simple insect brains. We have recently demonstrated how it is possible to implement large-scale artificial neural networks and real-time sensory motor systems in VLSI technology, exploiting the physics of silicon to reproduce the biophysics of neural systems. But the main bottleneck is in the understanding of how to use these systems to perform general purpose computation. Progress in this domain can be achieved only by pursuing a fully integrated multi-disciplinary approach. We propose to combine neuroscience, mathematics, computer-science, and engineering to develop a theoretical formalism and its supporting technology for designing spike-based general purpose “neuromorphic processors”, as distributed multi-chip neuromorphic VLSI systems, and for programming them to learn to produce desired computations autonomously. We will study the properties of neural circuits in the neocortex, model their coding strategies and spike-driven learning mechanisms using biophysically realistic spiking neural networks, and implement them using hybrid analog digital VLSI circuits. By interfacing these systems to silicon retinas, cochleas and autonomous robotic platforms we will build embodied neuromorphic processors able to carry out general event-based computations in real-world behavioral tasks.
This is part of a larger scale EU project (SCANDLE: accoustic SCene ANalysis for Detecting Living Entities), which involves five different groups, spread across five different countries. Our contribution will be the development of neurocomputational models and neuromorphic architectures that support the computational primitives for implementing cognitive acoustic scene analysis. These include VLSI networks of spiking neurons with spike-based plasticity learning rules, and neuromorphic VLSI hardware capable of asynchronous, stimulus-driven, real-time classification.
eMorph is a project funded by the Seventh Research
Program (FP7) of the European Union. It involves 4 research groups in 3
countries. The goal of eMorph is to design asynchronous vision sensors with non-uniform
morphology, using analog VLSI neuromorphic circuits, and to develop a
supporting data-driven asynchronous computational paradigm for
machine-vision that is radically different from conventional image
We are developing a full-fledged audio/visual selective attention
system using custom neuromorphic VLSI devices, able to operate in
real-time, with low power, and that can be packaged into a compact system. The neuromorphic approach aims to implement the
principles of computation used by the nervous systems in analog/digital
VLSI technology, exploiting the device physics of transistors to
reproduce the biophysics of neural cells. The neuromorphic devices
being used faithfully model detail properties of biological selective
attention systems down to the single neuron and single synapse
dynamics, and respond to sensory stimuli in real-time.
We are developing an
event-driven sound recognition system based on
biological principles, and uses real-time low-power neuromorphic VLSI
technology. We take advantage of recent advances in understanding
auditory perception up to cortical levels of cognitive processing, and
at the same time exploit the progress made in neuromorphic engineering
that offers the possibility of building robust, massively parallel,
data-driven implementations of biologically realistic processing, in
We are carrying out an assessment study on “neuromorphic computation of optic flow data” by combining top expertise in custom neuromorphic VLSI motion sensor design with real-time insect flight behavior and control analysis. Specifically, we are exploiting the unique ability of our lab to study in-flight behavior of insects in real-time, for reverse engineering their ability to respond to both transversal and expanding optic flow, and combine it with our ability to design state-of-the-art neuromorphic VLSI motion sensors, for building compact low-power neuromorphic controllers.
Long-term (always running) projects
Internships, theses, student projects, and undergraduate research opportunities
UZH - ETH Zurich students:
If you are interested in working on one of the projects listed above, there is always the possibility to define sub-projects and objectives suitable for Master theses and Semesterarbeits. Please contact Giacomo Indiveri directly, and arrange a meeting with him.
Unfortunately we don't have any instruments to provide financial support for intern-ships or thesis projects. However, if you find alternative sources of funding or can provide your own financial support, we can define student/thesis projects, provide the necessary lab and office space, and supervise your work. Given the experimental nature of the work being carried out in our lab, involving the design or use of custom analog VLSI devices, it only makes sense to consider project durations of at least 6 months.
Please make sure you can demonstrate your financial support capabilities (mainly for VISA issues) before contacting Giacomo Indiveri about this.