NICE #8

(The NICE#8 was initially planned to take place in 2020, but had to be postponed to 2021 due to COVID-19.)

Note: the exact order and timing of the talks is so far draft!

Times in the agenda are in CET (Berlin), EDT (New York), PDT (Los Angeles) and UTC. (Some other time zones: Australia, Japan, China, India, ... or only CET ... )

Meeting venue:

• online as zoom video conference (live talks and Q and A). The zoom video conference client software (free of charge, available for Windows, Mac and Linux at zoom.us, also available for iOS and Android in the respective app stores ) is required.
• please register here for NICE 2021

NEUROTECH Forum (15 March 2021)

Info: just before NICE on 15 March 2021 the NEUROTECH Forum II will take place online (free of charge. Registration for the forum event). The topic is "Neuromorphic Computing Technologies: Opportunities, challenges and Applications Roadmap".

Welcome to NICE #8

Organizer Round

Keynote: Lessons from Loihi for the Future of Neuromorphic Computing

show abstract

Why is Neuromorphic Event-based Engineering the future of AI?

The BrainScaleS mobile platform

show abstract

(break)

Group photo (zoom screenshots)

Evaluating complexity and resilience trade-offs in emerging memory inference machines

Lightning talk: From clean room to machine room: towards accelerated cortical simulations on the BrainScaleS wafer-scale system

show abstract

Closed-loop experiments on the BrainScaleS-2 architecture

show abstract

Batch << 1: Why Neuromorphic Computing Architectures Suit Real-Time Workloads

Neuromorphic and AI research at BCAI (Bosch Center for Artificial Intelligence)

Mapping Deep Neural Networks on SpiNNaker2

Open mic / discussion

End of day I

(break)

Tutorials: BrainScaleS and DYNAP-SE

Two tutorials/hands on in parallel:

• BrainScaleS (note: the same BrainScaleS hands on tutorial is also offered on Thursday, 10:00-13:00h CET)
  • about 30 min introduction
  • hands-on usage of the BrainScaleS system (via web browser). Limited number of participants.
• DYNAP-SE (note:the same DYNAP-SE hands on tutorial is also offered on Friday morning)
  • 1-hour live/interactive Dynapse demo: demo on a real Dynapse, take questions and implementing small changes from the audience.
  • 2-hour guided session where participants run a Jupyter notebook with simulations modelling Dynapse. This part is limited to 15 people per session.

For a description please see the tutorials page.

Tutorial: SpiNNaker hands-on

(Note: the same SpiNNaker hands on tutorial is also offered on Thursday, 21:00 - 22:30h CET)

For a description please see the tutorials page.

(break)

NICE - day II

Keynote: From Brains to Silicon -- Applying lessons from neuroscience to machine learning

show abstract

A Neuromorphic Future for Classic Computing Tasks

Lightning talk: Benchmarking of Neuromorphic Hardware Systems

show abstract

Natural density cortical models as benchmarks for universal neuromorphic computers

show abstract

Poster Lightning Talks

1 min - 1 slide poster appetizers

Poster session A and coffee

Platform-Agnostic Neural Algorithm Composition using Fugu

Lightning talk: Implementing Backpropagation for Learning on Neuromorphic Spiking Hardware

show abstract

Inductive bias transfer between brains and machines

show abstract

Lightning talk: Spike Latency Reduction generates Efficient Predictive Coding

show abstract

Lightning talk: Cognitive Domain Ontologies: HPCs to Ultra Low Power Neuromorphic Platforms

show abstract

Open mic / discussion

(break)

Tutorial: BrainScaleS hands-on

(Note: the same BrainScaleS hands on tutorial is also offered on Tuesday evening)

• about 30 min introduction
• hands-on usage of the BrainScaleS system (via web browser). Limited number of participants.

For a description of the pre-requirements, please see the tutorials page.

(break)

NICE - day III

Keynote: Biological inspiration for improving computing and learning in spiking neural networks

show abstract

On the computational power and complexity of Spiking Neural Networks

Evolutionary Optimization for Neuromorphic Systems

show abstract

An event-based gas sensing device that resolves fast transients in a turbulent environment

Sequence learning, prediction, and generation in networks of spiking neurons

Sequence learning, prediction and generation has been proposed to be the universal computation performed by the neocortex. The Hierarchical Temporal Memory (HTM) algorithm realizes this form of computation. It learns sequences in an unsupervised and continuous manner using local learning rules, permits a context-specific prediction of future sequence elements, and generates mismatch signals in case the predictions are not met. While the HTM algorithm accounts for a number of biological features such as topographic receptive fields, nonlinear dendritic processing, and sparse connectivity, it is based on abstract discrete-time neuron and synapse dynamics, as well as on plasticity mechanisms that can only partly be related to known biological mechanisms.

Here, we devise a continuous-time implementation of the temporal-memory (TM) component of the HTM algorithm, which is based on a recurrent network of spiking neurons with biophysically interpretable variables and parameters. The model learns non-Markovian sequences by means of a structural Hebbian synaptic plasticity mechanism supplemented with a rate-based homeostatic control. In combination with nonlinear dendritic input integration and local inhibitory feedback, this type of plasticity leads to the dynamic self-organization of narrow sequence-specific feedforward subnetworks. These subnetworks provide the substrate for a faithful propagation of sparse, synchronous activity, and, thereby, for a robust, context-specific prediction of future sequence elements as well as for the autonomous replay of previously learned sequences.

By strengthening the link to biology, our implementation facilitates the evaluation of the TM hypothesis based on experimentally accessible quantities. The continuous-time implementation of the TM algorithm permits, in particular, an investigation of the role of sequence timing for sequence learning, prediction and replay. We demonstrate this aspect by studying the effect of the sequence speed on the sequence learning performance and on the speed of autonomous sequence replay.

Poster session b and coffee

Conductance-based dendrites perform reliability-weighted opinion pooling

show abstract

Lightning talk: Natural gradient learning for spiking neurons

show abstract

Making spiking neurons more succinct with multi-compartment models

Lightning talk: The Computational Capacity of Mem-LRC Reservoirs

Open mic / discussion

(break)

Tutorial: SpiNNaker hands-on

(Note: the same SpiNNaker hands on tutorial is also offered on Wednesday, 10:30-12:00h CET)

For a description please see the tutorials page.

Tutorial:: DYNAP-SE

(Note: the same DYNAP-SE tutorial is also offered on Tuesday evening)

• 1-hour live/interactive Dynapse demo: demo on a real Dynapse, take questions and implementing small changes from the audience.
• 2-hour guided session where participants run a Jupyter notebook with simulations modelling Dynapse. This part is limited to 15 people per session.

(break)

NICE - day IV

Keynote: Bottom-up and top-down neuromorphic processor design: Unveiling roads to embedded cognition

show abstract

Lightning talk: Subspace Locally Competitive Algorithms

show abstract

Programming neuromorphic computers: PyNN and beyond

Lightning talk: TBD

BrainScaleS: Development Methodologies and Operating System

show abstract

Lightning talk: Evolving Spiking Neural Networks for Robot Sensory-motor Decision Tasks of Varying Difficulty

show abstract

Coffee break

Relational Neurogenesis for Lifelong Learning Agents

Lightning talk: Fast and deep neuromorphic learning with first-spike coding

show abstract

Lightning talk: Neuromorphic Computing for Spacecraft’s Terrain Relative Navigation: A Case of Event-Based Crater Classification Task

Beyond Backprop: Different Approaches to Credit Assignment in Neural Nets

show abstract

Lightning talk: Comparing Neural Accelerators & Neuromorphic Architectures The False Idol of Operations

show abstract

Real-time Mapping on a Neuromorphic Processor

show abstract

Wrap up / farewell

End of NICE 2021