Work Groups

Solving Constraint Satisfaction Problems on Neuromorphic Chips (Dynap-se)

Solving constraint satisfaction problems (CSPs) is a notoriously expensive computational task, for example, Sudoku, Boolean Satisfiability Problem, etc. In this work-group, we will build a network to solve some typical constraint satisfaction problems on neuromorphic chips.

To accelerate the searching of optimal solutions, we will utilize the randomness brought by ...

GPU-accelerated brain simulations

GeNN is an open source library for generating code to accelerate neural network simulations on NVIDIA GPUs. As these are becoming commonplace, the first aim of this workgroup is to help any interested users get up and running with GeNN and use it to accelerate the simulation of their own ...

Learning Cognitive Maps in Neuromorphic Hardware

In this work group, we will combine a dynamic neural fields-based architecture for one-shot recognition of places (objects) with a grid/place-cells inspired architecture for representing space and an architecture for learning sequences to arrive at a map-building system. We will aim for implementing the neural architecture in neuromorphic hardware ...

Unsupervised learning using WTA networks in neuromorphic hardware

In this project we will show that simple objects can be learned by neuromorphic hardware in real-time and with low power consumption when configured in a ‘soft’ Winner-Take-All (WTA) network and by exploiting the variability of the silicon neurons on the chip. We will use a neuromorphic processor with 256 ...

Online Learning in Digital Hardware, Deep Convolutional STDP

STDP is a bio-inspired learning rule that can be implemented locally in neurons (without a global supervisor). This will allow the rule to be implemented in massively parallel platforms without extra overhead. In this project, we start from understanding the Convolutional STDP learning rule and Hierarchical multi-layer version of the ...

SpiNNaker software install

session for installing the latest software release from the spinnaker software team.

PyNN 08 and PyNN 0.75 and SpiNNaker

The new release of the SpiNNaker software supports a basic implementation of PyNN 0.8 which runs on SpiNNaker. Come and try it out.

Using SpiNNaker for your Stuff!

If you want to use SpiNNaker for any of your own work-groups projects, this is the work-group for you.

Giving SpiNNaker2 Eyes and other Senses

In this work group, we will explore connecting neuromorphic sensors to the second-generation SpiNNaker prototype. We will connect a DVS to it and explore its integration with SpiNNaker2 in some simple vision tasks, and we are looking forward to trying out other neuromorphic sensors. Also, we want to explore how ...

Neuromorphic target acquisition based on auditory cues

It was shown that it possible to acquire and follow a visual target with a fully neuromorphic close loop setup [1]. The system features a robot equipped with a Dynamic Vision Sensors (DVS) which extracts a target (blinking LED) from background activity. The relative position of the target is then ...

Training deep spiking networks with the N2D2 deep learning framework

The N2D2 deep learning library is a new open-source C++ based deep learning framework launched by CEA.

Despite its lightweight implementation (it should run on most Ubuntu systems without installing additional dependencies), N2D2 is capable of implementing all state-of-the art networks for image recognition (LeNet, GoogleNet). Most architectures can be ...

Neuromorphic auditory sensor applications using SpiNNaker

Auditory environment analysis could be useful for robot navigation helping. Doppler effect give cues about how objects are moving in a scenario. In this workgroup we propose to use a spike-based Neuromorphic Auditory Sensor connected to a 4-chip SpiNNaker board for determining if an object is moving to or from ...

Discussion Groups

Educating the next generation of neuromorphic engineers

In this discussion group we aim to summarise material, examples and experience of how to educate students that are interested to learn about neuromorphic engineering and problem solving using modern neural network concepts, methods, implementations and neuromorphic hardware.

Spiking self-organizing maps for deep learning

Convolutional Neural Networks have been shown to successfully classify and localize objects within static images. Furthermore, the learned features show a strong resemblance with receptive fields of neurons found in the early visual cortex. It is yet not clear how from this kind of feature representation one could build models ...

Neuromorphic robot controllers: why, when, how?

Short abstract: In this discussion group we will talk about the place for neuromorphic controllers in the overall landscape of driving and table-top robots, discuss the challenges of integrating neuromorphic and robotic hardware, and set the goals for future research towards neuromorphic robots.

Insect brains as inspiration for neuromorphic systems

The discussion could take a number of turns but could include olfactory sensing and recognition, vision based navigation and primitive forms of decision making.

Real-time processing of temporal data

The group would deal with design of a system that can perform tasks such as ECG (Echo-cardiogram) pattern classification or EMG (Electromyogram) classification.

The focus would to think of a system-level architecture with a necessary software and hardware framework that can implement a pattern recognition task in real-time. A candidate ...

Recreational Groups


If the weather is nice, join for a cold bath in either the pool or the even colder sea!

(beach is 15 min later)

Tea tasting

try some teas, try to diagnose which are which, just relax with a cuppa.

Playing cards

chill, relax the evening away learning new card games.