NICE 2020

(For printing: the agenda without borders) (show all abstracts)
Monday, 16 March 2020

NICE 2020 in Heidelberg

Meeting venue: Kirchhoff-Institute for Physics, Im Neuenheimer Feld 227, D-69117 Heidelberg, Germany

Pre-NICE events on Monday, 16 March 2020

The special event will be organized by the NEUROTECH project.

Travel info:

  • Getting to the venue:
    • the nearest tram stop to the meeting venue is "Heidelberg Bunsengymnasium" (marked in the map linked above) [online timetable]https://reiseauskunft.bahn.de//bin/query.exe/en?Z=Neuenheim+Bunsengymnasium,+Heidelberg), provided by German Railway. Here you can also buy tickets online
  • Getting to Heidelberg

Hotels: These hotels are relatively close to the meeting venue (Kirchhoff-Institute for Physics, see the map above). A lot more hotels are listed in online hotel booking sites (e.g. on booking.com)

.

19:30-21:30
(120 min)

NICE 2020 Welcome reception

at the meeting venue.

The reception is also open for the participants of the NEUROTECH event Future Application Directions for Neuromorphic Computing Technologies


Tuesday, 17 March 2020
08:45
NICE 2020, workshop day I

(Registration booth opens at 8:30h)

09:00-09:10
(10+5 min)
 Welcome to NICE 2020
09:15-09:45
(30 min)
 Organizer Round
09:45-10:25
(40+5 min)
 Keynote IMike Davies (Intel)
10:30-10:50
(20+5 min)
 Luping Shi (Tsinghua University)
11:00-11:30
(30 min)
 Coffee break
11:30-11:50
(20+5 min)
 Evaluating complexity and resilience trade-offs in emerging memory inference machines

show abstract

Christopher Bennett (Sandia National Labs)
11:55-12:15
(20+5 min)
 Johannes Schemmel (Heidelberg University)
12:20-12:30
(10+5 min)
 Lightning talk: From clean room to machine room: towards accelerated cortical simulations on the BrainScaleS wafer-scale system

show abstract

Sebastian Schmitt (Heidelberg University)
12:35-13:00
(25 min)
 Poster Lightning Talks

1 min - 1 slide poster appetizers

all Poster Presenters
13:00-14:30
(90 min)
 Lunch, poster setup, demonstrators setup
14:30-14:40
(10+5 min)
 Group photo at NICE

(The group photo will be placed on the internet. By showing up for the photo you grant your permission for the publication of the photo)

14:45-15:05
(20+5 min)
 Why is Neuromorphic Event-based Engineering the future of AI?

show abstract

Ryad Benjamin Benosman (UPITT/CMU/SORBONNE)
15:10-15:30
(20+5 min)
 Neuromorphic and AI research at BCAI (Bosch Center for Artificial Intelligence)

show abstract

Thomas Pfeil (Bosch Center for Artificial Intelligence)
15:35-15:55
(20+5 min)
 Mapping Deep Neural Networks on SpiNNaker2

show abstract

Florian Kelber (TU Dresden)
16:00-16:30
(30 min)
 Coffee break
16:30-16:50
(20+5 min)
 Closed-loop experiments on the BrainScaleS-2 architecture

show abstract

Korbinian Schreiber (Heidelberg University)
16:55-17:05
(10+5 min)
 Lightning talk: Adaptive control for hindlimb locomotion in a simulated mouse through temporal cerebellar learning

show abstract

Thomas Passer Jensen (Technical University of Denmark)
17:10-17:30
(20+5 min)
 (speaker cancelled)
17:35-18:20
(45 min)
 Open mic / discussions
19:00-21:30
(150 min)
 Poster dinner

The max. poster size is A0, orientation PORTRAIT (841 mm wide x 1189 mm high)


Wednesday, 18 March 2020
08:45
NICE 2020, workshpo day II
09:00-09:15
(15 min)
 Welcome / overview
09:15-09:55
(40+5 min)
 KeynoteWolfgang Maass (Graz University of Technology)
10:00-10:20
(20+5 min)
 On the computational power and complexity of Spiking Neural Networks

show abstract

Nils Donselaar (Radboud Universiteit Nijmegen)
10:25-10:45
(20+5 min)
 The speed of sequence processing in biological neuronal networks

show abstract

Younes Bouhadjar (Forschungszentrum Juelich)
11:00-11:30
(30 min)
 Coffee brek
11:30-11:50
(20+5 min)
 Walter Senn (Universität Bern)
11:55-12:15
(20+5 min)
 Conductance-based dendrites perform reliability-weighted opinion pooling

show abstract

Jakob Jordan (Institute of Physiology, University of Bern)
12:20-12:30
(10+5 min)
 Lightning talk: Natural gradient learning for spiking neurons

show abstract

Elena Kreutzer (University of Bern)
12:35-12:45
(10+5 min)
 Lightning talk: The Computational Capacity of Mem-LRC Reservoirs

show abstract

Forrest Sheldon (Los Alamos National Lab - T-4/CNLS)
13:00-14:00
(60 min)
 Lunch
14:00-14:20
(20+5 min)
 Making spiking neurons more succinct with multi-compartment models

show abstract

Johannes Leugering (Fraunhofer IIS)
14:25-14:45
(20+5 min)
 Evolutionary Optimization for Neuromorphic Systems

show abstract

Catherine Schuman (Oak Ridge )
14:50-15:00
(10+5 min)
 Lightning talk: Implementing Backpropagation for Learning on Neuromorphic Spiking Hardware

show abstract

Andrew Sornborger (Los Alamos National Laboratory)
15:05-15:15
(10+5 min)
 Lightning talk: Spike Latency Reduction generates Efficient Predictive Coding

show abstract

Pau Vilimelis Aceituno (Max Planck Institute for Mathematics in the Sciences)
15:20-16:10
(50 min)
 Special coffee break: EINC & BrainScaleS 1
16:10-16:20
(10+5 min)
 Lightning talk: Fast and deep neuromorphic learning with first-spike coding

show abstract

Julian Goeltz (Kirchhoff Institut fuer Physik, Universitaet Heidelberg)
16:25-16:35
(10+5 min)
 Lightning talk: Neuromorphic Graph Algorithms: Extracting Longest ShortestPaths and Minimum Spanning Trees

show abstract

(Bill Kay)
16:40-16:50
(10+5 min)
 Lightning talk: Subspace Locally Competitive Algorithms

show abstract

Dylan Paiton (University of Tübingen)
16:55-17:40
(45 min)
 Open mic / discussion
18:00-21:00
(180 min)
 Conference dinner

Thursday, 19 March 2020
08:45
NICE 2020, workshop day III
09:00-09:15
(15 min)
 Welcome / overview
09:15-09:55
(40+5 min)
 Keynote: Bottom-up and top-down neuromorphic processor design: Unveiling roads to embedded cognition

show abstract

Charlotte Frenkel (Institute of Neuroinformatics, Zürich, Switzerland)
10:00-10:20
(20+5 min)
 A Neuromorphic Future for Classic Computing Tasks

show abstract

Brad Aimone (Sandia National Laboratories)
10:25-10:35
(10+5 min)
 Lightning talk: Benchmarking of Neuromorphic Hardware Systems

show abstract

Christoph Ostrau (Bielefeld University)
10:40-10:50
(10+5 min)
 Lightning talk: Evolving Spiking Neural Networks for Robot Sensory-motor Decision Tasks of Varying Difficulty

show abstract

J. David Schaffer (Binghamton University)
11:00-11:30
(30 min)
 Coffee break
11:30-11:50
(20+5 min)
 Natural density cortical models as benchmarks for universal neuromorphic computersMarkus Diesmann (Forschungszentrum Jülich GmbH)
11:55-12:15
(20+5 min)
 Platform-Agnostic Neural Algorithm Composition using Fugu

show abstract

William Severa (Sandia National Laboratories)
12:20-12:40
(20+5 min)
 Programming neuromorphic computers: PyNN and beyond

show abstract

Andrew Davison (CNRS)
12:45-12:55
(10+5 min)
 Lightning talk: Caspian: A Neuromorphic Development Platform

show abstract

(John (Parker) Mitchell)
13:00-14:00
(60 min)
 Lunch
14:00-14:20
(20+5 min)
 BrainScaleS: Development Methodologies and Operating System

show abstract

Eric Müller
14:25-14:45
(20+5 min)
 Inductive bias transfer between brains and machines

show abstract

Fabian Sinz (University Tübingen)
14:50-15:00
(10+5 min)
 Lightning talk: Cognitive Domain Ontologies: HPCs to Ultra Low Power Neuromorphic Platforms

show abstract

Chris Yakopcic (University of Dayton)
15:05-15:15
(10+5 min)
 Lightning talk: Comparing Neural Accelerators & Neuromorphic Architectures The False Idol of Operations

show abstract

Craig Vineyard (Sandia National Laboratories )
15:20-15:40
(20+5 min)
 Real-time Mapping on a Neuromorphic Processor

show abstract

Guangzhi Tang et al.
15:45-15:55
(10+5 min)
 Lightning talk: Neuromorphic Computing for Spacecraft’s Terrain Relative Navigation: A Case of Event-Based Crater Classification Task

show abstract

Kazuki Kariya (The Graduate University for Advanced Studies, SOKENDAI)
16:00-16:30
(30 min)
 Coffee break
16:30-16:50
(20+5 min)
 Beyond Backprop: Different Approaches to Credit Assignment in Neural Nets

show abstract

Irina Rish (IBM)
16:55-17:15
(20+5 min)
 Batch << 1: Why Neuromorphic Computing Architectures Suit Real-Time Workloads

show abstract

Jonathan Tapson (GrAI Matter Labs)
17:20-17:40
(20+5 min)
 Relational Neurogenesis for Lifelong Learning Agents

Tej Pandit and Dhireesha Kudithipudi

Reinforcement learning systems have shown tremendous potential in being able to model meritorious behavior in virtual agents and robots. The ability to learn through continuous reinforcement and interaction with an environment negates the requirement of painstakingly curated datasets and hand crafted features. However, the ability to learn multiple tasks in a sequential manner, referred to as lifelong or continual learning, remains unresolved. Current implementations either concentrate on preserving information in fixed capacity networks, or propose incrementally growing networks which randomly search through an unconstrained solution space. This work proposes a novel algorithm for continual learning using neurogenesis in reinforcement learning agents. It builds upon existing neuroevolutionary techniques, and incorporates several new mechanisms for limiting the memory resources while expanding neural network learning capacity. The algorithm is tested on a custom set of sequential virtual environments which emulate meaningful scenarios.

Tej Pandit (University of Texas at San Antonio)
17:45-18:15
(30 min)
 open mic / discussions
18:15-18:30
(15 min)
 Wrap-up / adjourn
18:30
End of NICE 2020 for non-tutorial attendants
19:00-20:30
(90 min)
 Dinner (only for tutorial attendants)

Friday, 20 March 2020
09:00
NICE 2020, Tutorials day

The tutorial day can be booked as one of the registration options. On the tutorial day hands-on interactive tutorials with several different neuromorphic compute systems will be offered:

  • SpiNNaker tutorial (the SpiNNaker system in Manchester is available remotely via the HBP Collaboratoy)
  • Intel Loihi platform tutorial (Lecture style. To follow along from your own laptop your need to engage with Intel’s Neuromorphic Research Community beforehand (email inrc_interest@intel.com for more information).
  • BrainScaleS tutorial (the large scale BrainScaleS-1 system, available remotely via the HBP Collaboratoy, is physically located 50m from the tutorial site)

show abstract

09:00-11:30
(150 min)
 Tutorial (and coffee)

In parallel ("choose one"):

  • BrainScaleS
  • SpiNNaker
  • Loihi: an overview of the Loihi hardware architecture and SDK basics
11:30-12:30
(60 min)
 Lunch (only for tutorial participants)
12:30-15:00
(150 min)
 Tutorial (and coffee)

In parallel ("choose one"):

  • BrainScaleS
  • SpiNNaker
  • Loihi: live examples and step-by-step iPhython-based tutorials of a wide variety of algorithmic examples
15:00
End of the NICE 2020 tutorial day
Contact: bjoern.kindler@kip.uni-heidelberg.de
Agenda page for printing (also as short info or short info with end-time)