1 code implementation • 28 Sep 2023 • Gregor Lenz, Garrick Orchard, Sadique Sheik
We propose a temporal ANN-to-SNN conversion method, which we call Quartz, that is based on the time to first spike (TTFS).
1 code implementation • 16 Mar 2023 • Jonathan Timcheck, Sumit Bam Shrestha, Daniel Ben Dayan Rubin, Adam Kupryjanow, Garrick Orchard, Lukasz Pindor, Timothy Shea, Mike Davies
A critical enabler for progress in neuromorphic computing research is the ability to transparently evaluate different neuromorphic solutions on important tasks and to compare them to state-of-the-art conventional solutions.
no code implementations • 5 Nov 2021 • Garrick Orchard, E. Paxon Frady, Daniel Ben Dayan Rubin, Sophia Sanborn, Sumit Bam Shrestha, Friedrich T. Sommer, Mike Davies
The biologically inspired spiking neurons used in neuromorphic computing are nonlinear filters with dynamic state variables -- very different from the stateless neuron models used in deep learning.
1 code implementation • 2 Sep 2020 • Bharath Ramesh, Shihao Zhang, Hong Yang, Andres Ussa, Matthew Ong, Garrick Orchard, Cheng Xiang
On the other hand, when the object re-enters the field-of-view of the camera, a data-driven, global sliding window detector locates the object for subsequent tracking.
no code implementations • 3 Aug 2020 • Kenneth Stewart, Garrick Orchard, Sumit Bam Shrestha, Emre Neftci
We present the Surrogate-gradient Online Error-triggered Learning (SOEL) system for online few-shot learning on neuromorphic processors.
no code implementations • 27 Apr 2020 • E. Paxon Frady, Garrick Orchard, David Florey, Nabil Imam, Ruokun Liu, Joyesh Mishra, Jonathan Tse, Andreas Wild, Friedrich T. Sommer, Mike Davies
Neuromorphic computing applies insights from neuroscience to uncover innovations in computing technology.
no code implementations • 22 Oct 2019 • Andres Ussa, Luca Della Vedova, Vandana Reddy Padala, Deepak Singla, Jyotibdha Acharya, Charles Zhang Lei, Garrick Orchard, Arindam Basu, Bharath Ramesh
With the success of deep learning, object recognition systems that can be deployed for real-world applications are becoming commonplace.
no code implementations • 11 Oct 2019 • Kenneth Stewart, Garrick Orchard, Sumit Bam Shrestha, Emre Neftci
Recent work suggests that synaptic plasticity dynamics in biological models of neurons and neuromorphic hardware are compatible with gradient-based learning (Neftci et al., 2019).
no code implementations • 4 Oct 2019 • Jyotibdha Acharya, Andres Ussa Caycedo, Vandana Reddy Padala, Rishi Raj Sidhu Singh, Garrick Orchard, Bharath Ramesh, Arindam Basu
In this paper, we present EBBIOT-a novel paradigm for object tracking using stationary neuromorphic vision sensors in low-power sensor nodes for the Internet of Video Things (IoVT).
no code implementations • 24 Apr 2019 • Bharath Ramesh, Andres Ussa, Luca Della Vedova, Hong Yang, Garrick Orchard
We present the first purely event-based, energy-efficient approach for object detection and categorization using an event camera.
1 code implementation • 17 Apr 2019 • Guillermo Gallego, Tobi Delbruck, Garrick Orchard, Chiara Bartolozzi, Brian Taba, Andrea Censi, Stefan Leutenegger, Andrew Davison, Joerg Conradt, Kostas Daniilidis, Davide Scaramuzza
Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of microseconds), very high dynamic range (140 dB vs. 60 dB), low power consumption, and high pixel bandwidth (on the order of kHz) resulting in reduced motion blur.
2 code implementations • NeurIPS 2018 • Sumit Bam Shrestha, Garrick Orchard
Configuring deep Spiking Neural Networks (SNNs) is an exciting research avenue for low power spike event based computation.
no code implementations • 30 Oct 2017 • Bharath Ramesh, Hong Yang, Garrick Orchard, Ngoc Anh Le Thi, Shihao Zhang, Cheng Xiang
We introduce a generic visual descriptor, termed as distribution aware retinal transform (DART), that encodes the structural context using log-polar grids for event cameras.
no code implementations • 26 Oct 2017 • Germain Haessig, Andrew Cassidy, Rodrigo Alvarez, Ryad Benosman, Garrick Orchard
This paper describes a fully spike-based neural network for optical flow estimation from Dynamic Vision Sensor data.
1 code implementation • 31 Oct 2015 • Garrick Orchard, Ralph Etienne-Cummings
Visual motion estimation is a computationally intensive, but important task for sighted animals.
no code implementations • 31 Oct 2015 • Garrick Orchard, Jacob G. Martin, R. Jacob Vogelstein, Ralph Etienne-Cummings
Recognition of objects in still images has traditionally been regarded as a difficult computational problem.
no code implementations • 5 Aug 2015 • Garrick Orchard, Cedric Meyer, Ralph Etienne-Cummings, Christoph Posch, Nitish Thakor, Ryad Benosman
The asynchronous nature of these systems frees computation and communication from the rigid predetermined timing enforced by system clocks in conventional systems.