Friday, 20 March 2020 is the tutorial day of the NICE with two slots (morning and afternoon) with 3 parallel tutorials each. Registration for the day can be selected when registering for the NICE workshop.
SpiNNaker tutorial
Title: Running Spiking Neural Network Simulations on SpiNNaker
Description: This workshop will describe how to access the SpiNNaker platform, via both Jupyter Notebooks and the HBP Collaboratory. It will then discuss how to write spiking neural networks using the PyNN language to be executed on SpiNNaker, and introduce the integration with the HBP Neurorobotics environment. Participants will be given access to the Jupyter Notebook system from which they will be able to follow some lab examples, and then go on to create their own networks running on the platform, as well as create co-simulations with the robotics environment.
Structure:
- How to access SpiNNaker using Jupyter and the HBP Collaboratory
- How to use the NRP through the SpiNNaker Jupyter Service
- Running PyNN Simulations on SpiNNaker
- Run lab examples and write your own networks
Timing: The tutorial will run twice with roughly identical content, once in the morning and once in the afternoon, so it can be combined with another morning or afternoon tutorial.
Access: the SpiNNaker system in Manchester is available remotely via the HBP Collaboratoy. Please find here the access procedure.
Intel Loihi tutorial
Title: Intel Corporation Loihi and Nx SDK
Description: The tutorial will provide an introduction to the Loihi Neuromorphic Computing Platform and its Nx SDK development toolkit. The Loihi chip features a unique programmable microcode learning engine for on-chip spiking neural networks. The chip contains 128 neuromorphic cores and is fabricated in Intel’s 14nm process.
- A morning session will provide an overview of the Loihi hardware architecture and SDK basics, followed by
- an afternoon session sharing live examples and step-by-step iPhython-based tutorials of a wide variety of algorithmic examples.
Note that participants will not be able to follow along from their own laptops unless they engage with Intel’s Neuromorphic Research Community beforehand (email [email protected] for more information).
Timing: The morning and the afternoon sessions are fairly self-contained, so people can pick and choose and also attend the other tutorials, as they wish.
BrainScaleS tutorial
Title: Experiments on BrainScaleS
Description: The tutorial will provide an introduction to and hands-on experiment with the BrainScaleS accelerated analog neuromorphic hardware system. BrainScaleS is a mixed analog-digital design operating 1,000 times faster than real-time. BrainScaleS-2 features programmable on-chip learning capabilities and a new concept called dendritic computing, developed in close collaboration with neuroscientists. Participants will gain a familiarity with biologically inspired spiking neural networks, novel computation and local learning.
Timing: The tutorial will run twice with roughly identical content, once in the morning and once in the afternoon, so it can be combined with another morning or afternoon tutorial.
Access: the BrainScaleS-1 system in Heidelberg is available remotely via the HBP Collaboratoy. Please find here the access procedure.