Journal ArticleDOI
HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition
TLDR
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.Abstract:
This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. 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. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.read more
Citations
More filters
Posted Content
Matrix-LSTM: a Differentiable Recurrent Surface for Asynchronous Event-Based Data.
TL;DR: In this paper, a grid of Long Short-Term Memory (LSTM) cells is proposed to learn end-to-end task-dependent event-surfaces, which shows good flexibility and expressiveness on optical flow estimation.
Proceedings ArticleDOI
Towards neuromorphic control: A spiking neural network based PID controller for UAV
Rasmus Karnøe Stagsted,Antonio Vitale,Jonas Binz,Alpha Renner,Leon Bonde Larsen,Yulia Sandamirskaya +5 more
TL;DR: In this paper, a spiking neural network (SNN) based PID controller on a neuromorphic chip is presented, in which each spike carries information about the measured, control, or error value defined by the identity of the spiking neuron.
Posted Content
LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing
TL;DR: A leaky integrate and analog fire (LIAF) neuron model is proposed so that analog values can be transmitted among neurons, and a deep network termed LIAF-Net is built on it for efficient spatiotemporal processing.
Journal ArticleDOI
Effective AER Object Classification Using Segmented Probability-Maximization Learning in Spiking Neural Networks
TL;DR: This work proposes an AER object classification model using a novel segmented probability-maximization (SPA) learning algorithm, and shows that, compared to state-of-the-art methods, this model is more effective, but also requires less information to reach a certain level of accuracy.
Proceedings ArticleDOI
DET: A High-Resolution DVS Dataset for Lane Extraction
TL;DR: This work introduces Dynamic Vision Sensor (DVS), a type of event-based sensor to lane extraction task and builds a high-resolution DVS dataset for lane extraction (DET), which demonstrates that DET is quite challenging for even state-of-the-art lane extraction methods.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
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.
Proceedings Article
Large Scale Distributed Deep Networks
Jeffrey Dean,Greg S. Corrado,Rajat Monga,Kai Chen,Matthieu Devin,Mark Z. Mao,Marc'Aurelio Ranzato,Andrew W. Senior,Paul A. Tucker,Ke Yang,Quoc V. Le,Andrew Y. Ng +11 more
TL;DR: This paper considers the problem of training a deep network with billions of parameters using tens of thousands of CPU cores and develops two algorithms for large-scale distributed training, Downpour SGD and Sandblaster L-BFGS, which increase the scale and speed of deep network training.