Show this page for printing or as short info (with end time)

NICE 2021 - Agenda

(show all abstracts)
Tuesday, 16 March 2021

NICE #8


Talk videos

  • Talk videos, which the speakers made available for public viewing are linked in the agenda. Some videos are accessible only for meeting attendants (from their personal page)
  • Public videos are also available in the NICE YouTube channel in the NICE 2021 playlist

Chatserver

We have a chatserver for the workshop (please use the username / initial password from your meetings 'personal page' (URL in your email). Please ask talk-related questions in the respective talk-channel (linked here in the agenda).

"Proceedings"

The proceedings for NICE 2021 are actually papers for the postponed 2020 NICE. You can find papers for many of the presentations here: https://dl.acm.org/doi/proceedings/10.1145/3381755

CET: 14:00‑14:10
(10+5 min)
 
Welcome to NICE #8
show presentation.pdf (public accessible)

Link to chat channel

Johannes Schemmel (Heidelberg University)
CET: 14:15‑14:40
(25 min)
 
Organizer Round

Link to chat channel

CET: 14:40‑15:20
(40+5 min)
 
Keynote: Lessons from Loihi for the Future of Neuromorphic Computing
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Mike Davies (Intel)
CET: 15:25‑15:45
(20+5 min)
 
Why is Neuromorphic Event-based Engineering the future of AI?
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Ryad Benjamin Benosman (UPITT/CMU/SORBONNE)
CET: 15:50‑16:10
(20+5 min)
 
Exploring the possibilities of analog neuromorphic computing with BrainScaleS
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Johannes Schemmel (Heidelberg University)
CET: 16:15‑16:45
(30 min)
 
(break)
CET: 16:45‑16:55
(10 min)
 
Group photo (zoom screenshots)

Note: we want to publish the group photo publicly = please switch on you camera, if you agree to appear in the photo.

CET: 16:55‑17:15
(20+5 min)
 
Evaluating complexity and resilience trade-offs in emerging memory inference machines
show presentation.pdf (public accessible)

Link to chat channel

Christopher Bennett (Sandia National Labs)
CET: 17:20‑17:30
(10+5 min)
 
Lightning talk: From clean room to machine room: towards accelerated cortical simulations on the BrainScaleS wafer-scale system
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Sebastian Schmitt (Heidelberg University)
CET: 17:35‑17:55
(20+5 min)
 
Closed-loop experiments on the BrainScaleS-2 architecture
(the presentation .pdf is accessible for meeting attendants from their 'personal page'), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Korbinian Schreiber (Heidelberg University)
CET: 18:00‑18:20
(20+5 min)
 
Batch << 1: Why Neuromorphic Computing Architectures Suit Real-Time Workloads
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Jonathan Tapson (School of Electrical and Data Engineering, University of Technology Sydney)
CET: 18:25‑18:45
(20+5 min)
 
Neuromorphic and AI research at BCAI (Bosch Center for Artificial Intelligence)
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Thomas Pfeil (Bosch Center for Artificial Intelligence)
CET: 18:50‑19:10
(20+5 min)
 
Mapping Deep Neural Networks on SpiNNaker2
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Florian Kelber (TU Dresden)
CET: 19:15‑19:45
(30 min)
 
Open mic / discussion

Link to chat channel

CET: 19:45
End of day I
CET: 19:45‑20:45
(60 min)
(break)
CET: 21:00‑00:00
(180 min)
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). Please use the "Join Main" dial in from your personal info page to access this tutorial.
  • DYNAP-SE (note:the same DYNAP-SE hands on tutorial is also offered on Wednesday and Friday morning) Please use the "Join Parallel meeting" dial in from your personal info page to access this tutorial.
    • 1-hour live/interactive Dynapse demo: demo on a real Dynapse, take questions and implementing small changes from the audience. (this part of the tutorial is accessible for all NICE registered attendants)
    • 2-hour guided session where participants run a Jupyter notebook with simulations modelling Dynapse. This part is limited to 15 people per session.
      Link to Tutorial DYNAP-SE chat channel
      For talk videos see further down in the agenda (19 March)

For a description please see the tutorials page.


Wednesday, 17 March 2021
CET: 10:00
Tutorials: SpiNNaker and DYNAP-SE

Two tutorials in parallel:

  • Starting at 10:30h CET: SpiNNaker (note: the same SpiNNaker hands on tutorial is also offered on Thursday, 21:00 - 22:30h CET) Please use the "Join Main" dial in from your personal info page to access this tutorial.
  • Starting at 10:00h CET: DYNAP-SE (note:the same DYNAP-SE hands on tutorial is also offered on Tuesday evening and Friday morning) Please use the "Join Parallel meeting" dial in from your personal info page to access this tutorial.

For a description please see the tutorials page.

CET: 10:30‑11:15
(45 min)
 
SpiNNaker tutorial introduction

show talk video (YouTube) (local version)
Andrew Rowley (University of Manchester)
CET: 13:00‑14:00
(60 min)
(break)
CET: 14:00
NICE - day II
CET: 14:00‑14:40
(40+5 min)
Keynote: From Brains to Silicon -- Applying lessons from neuroscience to machine learning
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Jeff Hawkins (Numenta), Subutai Ahmad (Numenta)
CET: 14:45‑15:05
(20+5 min)
A Neuromorphic Future for Classic Computing Tasks

show talk video (YouTube) (local version)

show abstract

Link to chat channel

Brad Aimone (Sandia National Laboratories)
CET: 15:10‑15:20
(10+5 min)
Lightning talk: Benchmarking of Neuromorphic Hardware Systems
(the presentation .pdf is accessible for meeting attendants from their 'personal page'), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Christoph Ostrau (Bielefeld University)
CET: 15:25‑15:45
(20+5 min)
Natural density cortical models as benchmarks for universal neuromorphic computers
(the presentation .pdf is accessible for meeting attendants from their 'personal page')

show abstract

Link to chat channel

Markus Diesmann (Forschungszentrum Jülich GmbH)
CET: 15:50‑16:15
(25 min)
Poster Lightning Talks

1 min - 1 slide poster appetizers

  • Astrocyte-modulated neuromorphic Central Pattern Generator for Robot Locomotion on Intel's Loihi (Ioannis Polykretis)
  • Bio-inspired few-shot learning with spiking neural networks (Garibaldi Pineda Garcia)
  • BrainScaleS Large Scale Spike Communication using Extoll (Tobias Thommes)
  • Critical Limits in a Bump Attractor Network of Spiking Neurons (Alberto Vergani)
  • Deep reinforcement learning for time-continuous substrates (Akos Ferenc Kungl)
  • Energy Constraints Improve Liquid State Machine Performance (Andrew Fountain)
  • Machine Perception: Similarity Representation while Learning in the Wild (Ayon Borthakur)
  • Structural plasticity on spiking neuromorphic hardware (Benjamin Cramer)
  • Training Delays in Spiking Neural Networks (Pau Vilimelis Aceituno)
  • IOP Publishing: new open access journal Neuromorphic Computing and Engineering

Talk-posters:

  • Neuroevolution with Scaleup (J. David Schaffer)
Alberto Vergani (AMU), Pau Vilimelis Aceituno (ETH Zürich), Benjamin Cramer (Heidelberg University), Garibaldi Pineda Garcia (University of Sussex), Ioannis Polykretis (Rutgers University), Tobias Thommes (Heidelberg University), Andrew Fountain (Rochester Institute of Technology), Ayon Borthakur (Cornell University), Akos Ferenc Kungl (Heidelberg University)
CET: 16:15‑17:15
(60 min)
Poster session A (and break)

CET: 17:15‑17:35
(20+5 min)
Platform-Agnostic Neural Algorithm Composition using Fugu
(the presentation .pdf is accessible for meeting attendants from their 'personal page'), (a video of this talk is available for meeting attendants. Please check your personal meeting page (for EBRAINS account owners: personal meeting page and show video))

show abstract

Link to chat channel

William Severa (Sandia National Laboratories)
CET: 17:40‑17:50
(10+5 min)
Lightning talk: Implementing Backpropagation for Learning on Neuromorphic Spiking Hardware
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Andrew Sornborger (Los Alamos National Laboratory)
CET: 17:55‑18:15
(20+5 min)
Inductive bias transfer between brains and machines
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Fabian Sinz (University Tübingen)
CET: 18:20‑18:30
(10+5 min)
Lightning talk: Spike Latency Reduction generates Efficient Predictive Coding
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Pau Vilimelis Aceituno (ETH Zürich)
CET: 18:35‑18:45
(10+5 min)
Lightning talk: Cognitive Domain Ontologies: HPCs to Ultra Low Power Neuromorphic Platforms
(the presentation .pdf is accessible for meeting attendants from their 'personal page')

show abstract

Link to chat channel

Chris Yakopcic (University of Dayton)
CET: 18:50‑19:20
(30 min)
Open mic / discussion

Link to chat channel

CET: 19:20‑20:20
(60 min)
(break)
CET: 20:30
Tutorial: Loihi

We’ll cover a few new “advanced” topics of interest to the community. These are

  • Characterizing energy and performance of Loihi workloads
  • Solving and constraint satisfaction problems on Loihi and benchmarking them to a state-of-the-art CPU solver
  • Training deep SNNs for Loihi with SLAYER

We’ll present on these topics and show some code running. Anyone who has access to Loihi will be able to find and run the code themselves, but we’d like to clarify that access to Loihi is not required for attending the tutorials. (If you want to get access to Loihi, please email inrc_interest@intel.com to get legal access to the Loihi cloud systems.)

Link to chat channel

CET: 20:30‑20:37
(7 min)
 
Intel Loihi's NxSDK: Introduction and overview
show presentation.pdf (public accessible), show talk video (YouTube) (local version)
Andreas Wild (Intel Corporation)
CET: 20:37‑21:18
(41 min)
 
A Fast and Efficient Constraint Satisfaction Solver on Loihi

show talk video (YouTube) (local version)
Gabriel Andres Fonseca Guerra (Intel Coorporation)
CET: 21:18‑21:52
(34 min)
 
SLAYER for Loihi
show presentation.pdf (public accessible), show talk video (YouTube) (local version)
Sumit Bam Shrestha (Intel Corporation)
CET: 21:52‑22:49
(57 min)
 
Performance Characterization on Loihi

show talk video (YouTube) (local version)
Garrick Orchard (Intel Corporation)

Thursday, 18 March 2021
CET: 10:00
Tutorial: BrainScaleS hands-on

Please use the "Join_Main" dial in on your personal page to attend.

  • 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.

Link to chat channel

CET: 10:00‑11:00
(60 min)
 
BrainScaleS-2 hands-on introduction, part I: Spiking mode

show talk video (YouTube) (local version)
Sebastian Billaudelle (Kirchhoff Institute for Physics, Heidelberg University)
CET: 11:00‑11:15
(15 min)
 
BrainScaleS-2 hands-on introduction, part II: Matrix multiplication mode

show talk video (YouTube) (local version)
Johannes Weis (Kirchhoff-Institute for Physics, Heidelberg University)
CET: 11:15‑11:50
(35 min)
 
BrainScaleS-2 hands-on introduction, part III: Matrix multiplication mode II

show talk video (YouTube) (local version)
Arne Emmel (Universität Heidelberg)
CET: 11:50‑12:50
(60 min)
 
(hands-on work with the BSS-2 single chip system)
CET: 13:00‑14:00
(60 min)
(break)
CET: 14:00
NICE - day III

Please use the "Join_Main" dial in on your personal page to attend.

CET: 14:00‑14:40
(40+5 min)
Keynote: Biological inspiration for improving computing and learning in spiking neural networks
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Wolfgang Maass (Graz University of Technology)
CET: 14:45‑15:05
(20+5 min)
On the computational power and complexity of Spiking Neural Networks
show presentation.pdf (public accessible)

show abstract

Link to chat channel

Johan Kwisthout (Radboud Universiteit Nijmegen)
CET: 15:10‑15:30
(20+5 min)
Evolutionary Optimization for Neuromorphic Systems
(the presentation .pdf is accessible for meeting attendants from their 'personal page'), (a video of this talk is available for meeting attendants. Please check your personal meeting page (for EBRAINS account owners: personal meeting page and show video))

show abstract

Link to chat channel

Catherine Schuman (Oak Ridge)
CET: 15:35‑15:55
(20+5 min)
An event-based gas sensing device that resolves fast transients in a turbulent environment
(the presentation .pdf is accessible for meeting attendants from their 'personal page'), (a video of this talk is available for meeting attendants. Please check your personal meeting page (for EBRAINS account owners: personal meeting page and show video))

show abstract

Link to chat channel

Michael Schmuker (University of Hertfordshire), Damien Drix (University of Hertfordshire)
CET: 16:00‑16:20
(20+5 min)
Sequence learning, prediction, and generation in networks of spiking neurons
(the presentation .pdf is accessible for meeting attendants from their 'personal page'), (a video of this talk is available for meeting attendants. Please check your personal meeting page (for EBRAINS account owners: personal meeting page and show video))

show abstract

Link to chat channel

Younes Bouhadjar (Forschungszentrum Juelich)
CET: 16:25‑17:25
(60 min)
Poster session b (and break)

For posters:

  • Energy Constraints Improve Liquid State Machine Performance (Andrew Fountain)
    poster.pdf and poster chat channel
  • Machine Perception: Similarity Representation while Learning in the Wild (Ayon Borthakur)
    poster.pdf and poster chat channel
  • Structural plasticity on spiking neuromorphic hardware (Benjamin Cramer)
    poster.pdf and poster chat channel
  • Training Delays in Spiking Neural Networks (Pau Vilimelis Aceituno)
    poster.pdf and poster chat channel

And for talk posters by:

  • Younes Bouhadjar: "Sequence learning, prediction, and generation in networks of spiking neurons"
    talk chat channel
  • Dylan Paiton: "Subspace Locally Competitive Algorithms"
    poster.pdf and the talk chat channel
  • J. David Schaffer: Evolving Spiking Neural Networks for Robot Sensory-motor Decision Tasks of Varying Difficulty
    poster.pdf and chat channel
  • Michael Schmuker / Damien Drix: An event-based gas sensing device that resolves fast transients in a turbulent environment
    poster.pdf and talk chat channel
CET: 17:25‑17:45
(20+5 min)
Lessons from neurobiology and physics: pseudobackprop & more

show abstract

Link to chat channel

Walter Senn (Universität Bern)
CET: 17:50‑18:10
(20+5 min)
Conductance-based dendrites perform reliability-weighted opinion pooling
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Jakob Jordan (Institute of Physiology, University of Bern)
CET: 18:15‑18:25
(10+5 min)
Lightning talk: Natural gradient learning for spiking neurons
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Elena Kreutzer (University of Bern)
CET: 18:30‑18:50
(20+5 min)
Making spiking neurons more succinct with multi-compartment models
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Johannes Leugering (Fraunhofer IIS)
CET: 18:55‑19:05
(10+5 min)
Lightning talk: The Computational Capacity of Mem-LRC Reservoirs
(the presentation .pdf is accessible for meeting attendants from their 'personal page')

show abstract

Link to chat channel

Forrest Sheldon (Los Alamos National Lab - T-4/CNLS)
CET: 19:10‑19:40
(30 min)
Open mic / discussion

Link to chat channel

CET: 19:40‑20:50
(70 min)
(break)
CET: 21:00‑22:30
(90 min)
Tutorial: SpiNNaker hands-on

For a recording of the introduction, please see the agenda entry for 17 March in the morning.

For a description please see the tutorials page.

Link to chat channel


Friday, 19 March 2021
CET: 10:00
Tutorial:: DYNAP-SE

Please use the "Join_Main" dial in on your personal page to attend.

  • 1-hour live/interactive Dynapse demo: demo on a real Dynapse, take questions and implementing small changes from the audience. (this part of the tutorial is accessible for all NICE registered attendants)
  • 2-hour guided session where participants run a Jupyter notebook with simulations modelling Dynapse. This part is limited to 15 people per session.

Link to chat channel

CET: 10:00‑10:20
(20 min)
 
Dynap-SE1 Demo Session

show talk video (YouTube) (local version)
Yigit Demirag (The Institute of Neuroinformatics, UZH and ETH Zürich)
CET: 10:20‑10:35
(15 min)
 
Remote demo of the Dynap-SE board

(a video of this talk is available for meeting attendants. Please check your personal meeting page (for EBRAINS account owners: personal meeting page and show video))
Dmitrii Zendrikov (Institute of Neuroinformatics, UZH and ETH Zurich)
CET: 10:35‑10:38
(3 min)
 
DYNAP-SE tutorial session 2: Simulating Dynap-SE1

show talk video (YouTube) (local version)
Yigit Demirag (The Institute of Neuroinformatics, UZH and ETH Zürich)
CET: 13:00‑14:00
(60 min)
(break)
CET: 14:00
NICE - day IV

Please use the "Join_Main" dial in on your personal page to attend.

CET: 14:00‑14:40
(40+5 min)
Keynote: Bottom-up and top-down neuromorphic processor design: Unveiling roads to embedded cognition
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Charlotte Frenkel (Institute of Neuroinformatics, Zürich, Switzerland)
CET: 14:45‑14:55
(10+5 min)
Lightning talk: Subspace Locally Competitive Algorithms
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Dylan Paiton (University of Tübingen)
CET: 15:00‑15:20
(20+5 min)
Programming neuromorphic computers: PyNN and beyond
show presentation.pdf (public accessible), show talk video

show abstract

Link to chat channel

Andrew Davison (CNRS)
CET: 15:25‑15:35
(10+5 min)
Lightning talk: Neuromorphic Graph Algorithms : Cycle Detection, Odd Cycle Detection, and Max Flow

show talk video (YouTube) (local version)

show abstract

Link to chat channel

William Kay (Oak Ridge National Laboratory)
CET: 15:40‑16:00
(20+5 min)
BrainScaleS: Development Methodologies and Operating System
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Eric Müller (Heidelberg University)
CET: 16:05‑16:15
(10+5 min)
Lightning talk: Evolving Spiking Neural Networks for Robot Sensory-motor Decision Tasks of Varying Difficulty
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

J. David Schaffer (Binghamton University)
CET: 16:20‑16:50
(30 min)
(break)
CET: 16:50‑17:10
(20+5 min)
Relational Neurogenesis for Lifelong Learning Agents
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Tej Pandit (University of Texas at San Antonio)
CET: 17:15‑17:25
(10+5 min)
Lightning talk: Fast and deep neuromorphic learning with first-spike coding
(the presentation .pdf is accessible for meeting attendants from their 'personal page'), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Julian Goeltz (Kirchhoff Institut fuer Physik, Universitaet Heidelberg)
CET: 17:30‑17:40
(10+5 min)
Lightning talk: Neuromorphic Computing for Spacecraft’s Terrain Relative Navigation: A Case of Event-Based Crater Classification Task
show presentation.pdf (public accessible), (a video of this talk is available for meeting attendants. Please check your personal meeting page (for EBRAINS account owners: personal meeting page and show video))

show abstract

Link to chat channel

Kazuki Kariya (The Graduate University for Advanced Studies, SOKENDAI)
CET: 17:45‑18:05
(20+5 min)
Beyond Backprop: Different Approaches to Credit Assignment in Neural Nets
show presentation.pdf (public accessible), show talk video (YouTube) (local version)

show abstract

Link to chat channel

Irina Rish (MILA / Université de Montréal)
CET: 18:10‑18:20
(10+5 min)
Lightning talk: Comparing Neural Accelerators & Neuromorphic Architectures The False Idol of Operations
show presentation.pdf (public accessible), (a video of this talk is available for meeting attendants. Please check your personal meeting page (for EBRAINS account owners: personal meeting page and show video))

show abstract

Link to chat channel

Craig Vineyard (Sandia National Laboratories)
CET: 18:25‑18:45
(20+5 min)
Real-time Mapping on a Neuromorphic Processor

show talk video (YouTube) (local version)

Navigation is so crucial for our survival that the brain hosts a dedicated network of neurons to map our surroundings. Place cells, grid cells, border cells, head direction cells and other specialized neurons in the hip- pocampus and the cortex work together in planning and learning maps of the environment [1]. When faced with similar navigation challenges, robots have an equally important need for generating a stable and accurate map. In our ongoing effort to translate the biological network for spatial navigation into a spiking neural network (SNN) that controls mobile robots in real-time, we first focused on simultaneous localization and mapping (SLAM), being one of the critical problems in robotics that relies highly on the accuracy of map representation [2]. Our approach allows us to leverage the asynchronous computing paradigm commonly found across brain areas and therefore has already demonstrated to be a significant energy-efficient solution for 1D SLAM [3], that can spur the emergence of the new neuromorphic processors, such as Intel’s Loihi [4] and IBM’s TrueNorth [5]. In this paper, we expand our previous work by proposing a SNN that forms a cognitive map of an unknown environment and is seamlessly integrated to Loihi.

[1] S. Poulter, T. Hartley, and C. Lever, "The neurobiology of mammalian navigation," Current Biology, vol. 28, no. 17, pp. R1023-R1042, 2018.

[2] G. Grisetti, C. Stachniss, and W. Burgard, "Improved techniques for grid mapping with rao-blackwellized particle filters," IEEE transactions on Robotics, vol. 23, no. 1, p. 34, 2007.

[3] G. Tang, A. Shah, and K. P. Michmizos, "Spiking neural network on neuromorphic hardware for energy- efficient unidimensional SLAM," in IEEE/RSJ International Conference onIntelligent Robots and Systems (IROS), Macau, China, 2019, pp. 1-6.

[4] M. Davies et al., "Loihi: A neuromorphic manycore processor with on-chip learning," IEEE Micro, vol. 38, no. 1, pp. 82-99, 2018.

[5] P. A. Merolla et al., "A million spiking-neuron integrated circuit with a scalable communication network and interface," Science, vol. 345, no. 6197, pp. 668-673, 2014.

Link to chat channel

Konstantinos Michmizos (Rutgers University)
CET: 18:50‑19:19
(29 min)
Opn mic / Wrap up

  • Best talk awards (by the NEUROTECH project):
    • Johannes Leugering (Fraunhofer)
    • Julian Göltz (Heidelberg University)
    • Charlotte Frenkel (Institute of Neuroinformatics)
    • Jakob Jordan (University of Bern)
CET: 19:19
Farewell .... and See you next year...
CET: 19:20
End of NICE 2021
Contact: bjoern.kindler@kip.uni-heidelberg.de