Tuesday, May 2, 2023 @ 8:00-9:00am PT / 17:00-18:00 CET you are invited to attend an INRC Forum talk from Prof. Jeff Orchard, University of Waterloo.
Hyperdimensional Algorithms using Spiking Phasors
Abstract: Hyperdimensional (HD) computing offers a powerful framework for representing compositional reasoning. Such algorithms lend themselves to neural-network implementations, allowing us to create neural networks that can perform cognitive functions, like spatial reasoning, arithmetic, and symbolic logic. But the vectors involved can be quite large. Advances in neuromorphic hardware hold the promise of reducing the running time and energy footprint of neural networks by orders of magnitude. In this talk, I will extend some pioneering work to run HD algorithms on a substrate of spiking neurons, implementing examples in spatial memory, function representation, and temporal memory.
Bio:
Jeff Orchard received degrees in applied mathematics from the University of Waterloo (BMath) and the University of British Columbia (MSc), and received his PhD in Computing Science from Simon Fraser University in 2003. Since then, he has been a faculty member at the Cheriton School of Computer Science at the University of Waterloo in Canada.
Prof. Orchard's research focuses on computational neuroscience, using mathematical models and computer simulations of neural networks in an effort to understand how the brain works. Guided by both theory and anatomy, he is building neural networks based on computational theories of the brain — such as predictive coding — to uncover the way we perceive the world. His research also includes Vector Symbolic Architectures and Algebras, spatial navigation, and population coding. He is a core member of the Centre for Theoretical Neuroscience.
Recording:
For the recording, see the full /wiki/spaces/forum/pages/1922629633 (accessible only to INRC Affiliates and Engaged Members).
If you are interested in becoming a member, here is the information about joining the INRC.
Tuesday, April 25, 2023 @ 8:00-9:00am PT / 17:00-18:00 CET you are invited to attend an INRC Forum talk from Dr. James Knight, University of Sussex.
Efficient training of sparse SNN classifiers using GeNN
Abstract: Intuitive and easy to use application programming interfaces such as Keras have played a large part in the rapid acceleration of ANN-based machine learning. We want to unlock the potential of spike-based machine learning in the same way, so here we present mlGeNN, an easy way to define, train and test spiking neural networks using GeNN — our efficient GPU-accelerated SNN simulator. Using GeNN, we demonstrate that we can use e-prop to train recurrent SNN classifiers on datasets including the Spiking Heidelberg Digits (SHD) and DVS gesture. We show that these classifiers can not only offer comparable performance to LSTMs but are up to 7× faster when performing inference on the same GPU hardware. As GeNN is designed to exploit sparse connectivity, by replacing the dense recurrent connectivity in classifier models with random sparse connectivity, we can reduce the time taken to train such models by almost 10× — although this results in some reduction in classification accuracy. However, in biological brains, alongside the changes to the strength of existing synapses driven by synaptic plasticity, structural plasticity prunes unused synapses and forms new ones. The Deep-R learning rule provides a framework for combining gradient-based learning with structural plasticity and by combining Deep-R with e-prop, we demonstrate that the aforementioned reduction in classification accuracy can be eliminated, even in very sparsely connected models.
Bio:
Jamie Knight received his BEng degree in Electronic Engineering from the University of Warwick in 2006. After working as a games-developer for several years, he received an MPhil in Advanced Computer Science from the University of Cambridge in 2013 and a PhD in Computer Science from the University of Manchester in 2016. His doctoral work focused on using the SpiNNaker neuromorphic supercomputer to simulate large-scale computational neuroscience models with synaptic plasticity. Since 2017 Jamie has worked at the University of Sussex, first as a Research Fellow focusing on using GPU hardware to accelerate spiking neural network-based robot controllers and, since 2022, as a EPSRC Research Software Engineering Fellow focusing on spike-based machine learning and the software to enable it.
Recording:
For the recording, see the full /wiki/spaces/forum/pages/1899790337 (accessible only to INRC Affiliates and Engaged Members).
If you are interested in becoming a member, here is the information about joining the INRC.
Tuesday, April 18, 2023 @ 8:00-9:00am PT / 17:00-18:00 CET you are invited to attend an INRC Forum talk from Dr. Akshit Saradagi, Luleå Tekniska Universitet.
Neuromorphic sensing in sub-terranean environments and neuromorphic solvers for model predictive control
Abstract: In this talk, I will be presenting some recent results in Neuromorphic Engineering from the Robotics and AI group at Luleå University of Technology, Sweden.
In the first half of my talk, I will be presenting a novel LiDAR and event camera fusion framework for fast and precise object and human detection in subterranean (SubT) environments. The fusion framework caters to the wide variety of adverse lighting conditions found in SubT environments, such as low or no light, high-contrast zones and in the presence of blinding light sources. The proposed fusion uses intensity filtering and K-means clustering on the LiDAR point cloud and frequency filtering and connectivity clustering on the events induced in an event camera by the returning LiDAR beams. The fusion framework was experimentally validated in a real SubT environment (a mine) with a Pioneer 3AT mobile robot. The experimental results show real-time performance for human detection and the NMPC-based controller allows for reactive tracking of a human or object of interest, even in complete darkness.
In the second half of the talk, I will be presenting our preliminary results on using neuromorphic solvers for solving quadratic programs arising in Model Predictive Control (MPC). More specifically, we employed the floating-point LAVA QP solver, which emulates the Proportional-Integral Projected Gradient (PIPG) Method for solving QP problems, to solve terminally constrained MPC problems. The objective function in linear MPC problems being strongly convex, the LAVA QP solver ensures that the distance to optimum and the constraint violation converge to zero at the rate of O(1/k^2) and O(1/k^3) respectively, with 'k' being the number of solver iterates. Given this peculiar convergence property of the solver, I will present a sketch of our proof for asymptotic stability of the closed loop system, along with the simulation-based validation.
Bio:
Akshit Saradagi is a Postdoctoral researcher in the Robotics and AI group at Luleå University of Technology, Sweden. He received his M.S and Ph.D dual degree from the Indian Institute of Technology Madras (IITM), Chennai, India. His current research focusses on distributed control of multi-agent systems, control barrier functions-based safety guarantees in Robotics, applications of Neuromorphic Computing in Robotics and control under resource constraints.
Recording:
For the recording, see the full /wiki/spaces/forum/pages/1899790337 (accessible only to INRC Affiliates and Engaged Members).
If you are interested in becoming a member, here is the information about joining the INRC.
The Intel Neuromorphic DNS Challenge is a unique opportunity to advance state-of-the-art neuromorphic algorithms research and win up to $55,000 of prize money.
Intel N-DNS Participant Orientation Meeting
Getting started with the Intel N-DNS Challenge? Join us for our participant orientation meeting! Intel Labs staff will present a short how-to for navigating the challenge repository, running the baseline solution, and reporting evaluation metrics, followed by a generous amount of time for open Q&A.
We will host two sessions to accommodate those working around the globe:
Pacific Evening Session: April 18, 8 pm PDT
Pacific Morning Session: April 19, 8 am PDT
The meetings will be recorded.
To get the most out of the participant orientation meeting, we recommend that you register via our Github beforehand.
We look forward to seeing you!
How to Join:
Microsoft Teams meeting links for the two sessions will be posted below nearer April 18.
April 18 8pm PT teams meeting link (Asia, Australia friendly)
April 19 8am PT teams meeting link (US, Europe friendly)