Open AccessPosted Content
A Sparse Coding Multi-Scale Precise-Timing Machine Learning Algorithm for Neuromorphic Event-Based Sensors
TL;DR: This work shows that the use of sparse coding allows for a very compact yet efficient time-based machine learning that lowers both the computational cost and memory need, and shows that it can represent visual scene temporal dynamics with a finite set of elementary time surfaces.
read more
Abstract: This paper introduces an unsupervised compact architecture that can extract features and classify the contents of dynamic scenes from the temporal output of a neuromorphic asynchronous event-based camera. Event-based cameras are clock-less sensors where each pixel asynchronously reports intensity changes encoded in time at the microsecond precision. While this technology is gaining more attention, there is still a lack of methodology and understanding of their temporal properties. This paper introduces an unsupervised time-oriented event-based machine learning algorithm building on the concept of hierarchy of temporal descriptors called time surfaces. In this work we show that the use of sparse coding allows for a very compact yet efficient time-based machine learning that lowers both the computational cost and memory need. We show that we can represent visual scene temporal dynamics with a finite set of elementary time surfaces while providing similar recognition rates as an uncompressed version by storing the most representative time surfaces using clustering techniques. Experiments will illustrate the main optimizations and trade-offs to consider when implementing the method for online continuous vs. offline learning. We report results on the same previously published 36 class character recognition task and a 4 class canonical dynamic card pip task, achieving 100% accuracy on each.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Event-Based Neuromorphic Vision for Autonomous Driving: A Paradigm Shift for Bio-Inspired Visual Sensing and Perception
TL;DR: It is expected that this article will serve as a starting point for new researchers and engineers in the autonomous driving field and provide a bird's-eye view to both neuromorphic vision and autonomous driving research communities.
284
Neuromorphic vision: From sensors to event-based algorithms
TL;DR: The state‐of‐the‐art event‐based vision algorithms are reviewed by categorizing them into three major vision applications, object detection/recognition, object tracking, localization and mapping, which enables more robustness.
32
Neural Coding Strategies for Event-Based Vision Data
Shane Harrigan,Sonya Coleman,Dermot Kerr,Pratheepan Yogarajah,Zheng Fang,Chengdong Wu +5 more
- 04 May 2020
TL;DR: Three different neural coding scheme formations for event-based vision data which are designed to emulate the neural behaviour exhibited by neurons under stimuli are introduced and determined that machine learning approaches, i.e. Convolutional Neural Network combined with a Stacked Autoencoder network, produce powerful descriptors of the patterns within events.
•Posted Content
When Conventional machine learning meets neuromorphic engineering: Deep Temporal Networks (DTNets) a machine learning frawmework allowing to operate on Events and Frames and implantable on Tensor Flow Like Hardware.
TL;DR: Preliminary results are introduced to show the efficiency of the principle of Deep Temporal Networks that allow to add time to convolutional networks by allowing deep integration principles not only using spatial information but also increasingly large temporal window.
1
References
Numerical recipes in C
William H. Press,Saul A. Teukolsky,William T. Vetterling,Brian P. Flannery +3 more
- 01 Jan 1994
TL;DR: The Diskette v 2.06, 3.5''[1.44M] for IBM PC, PS/2 and compatibles [DOS] Reference Record created on 2004-09-07, modified on 2016-08-08.
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
TL;DR: It is shown that a learning algorithm that attempts to find sparse linear codes for natural scenes will develop a complete family of localized, oriented, bandpass receptive fields, similar to those found in the primary visual cortex.
A QVGA 143 dB Dynamic Range Frame-Free PWM Image Sensor With Lossless Pixel-Level Video Compression and Time-Domain CDS
TL;DR: The biomimetic CMOS dynamic vision and image sensor described in this paper is based on a QVGA array of fully autonomous pixels containing event-based change detection and pulse-width-modulation imaging circuitry, which ideally results in lossless video compression through complete temporal redundancy suppression at the pixel level.
873
HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition
TL;DR: The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood and it is demonstrated that this concept can robustly be used at all stages of an event-based hierarchical model.
653
CAVIAR: A 45k Neuron, 5M Synapse, 12G Connects/s AER Hardware Sensory–Processing– Learning–Actuating System for High-Speed Visual Object Recognition and Tracking
R. Serrano-Gotarredona,M. Oster,P. Lichtsteiner,Alejandro Linares-Barranco,R. Paz-Vicente,F. Gomez-Rodriguez,Luis A. Camunas-Mesa,R Berner,M. Rivas-Perez,Tobi Delbruck,Shih-Chii Liu,Rodney J. Douglas,Philipp Hafliger,Gabriel Jimenez-Moreno,A.C. Ballcels,Teresa Serrano-Gotarredona,A.J. Acosta-Jimenez,Bernabe Linares-Barranco +17 more
TL;DR: CAVIAR is a massively parallel hardware implementation of a spike-based sensing-processing-learning-actuating system inspired by the physiology of the nervous system that achieves millisecond object recognition and tracking latencies.