Search Results for author: Ryad Benosman

Found 12 papers, 2 papers with code

Event Based Time-Vectors for auditory features extraction: a neuromorphic approach for low power audio recognition

no code implementations13 Dec 2021 Marco Rasetto, Juan P. Dominguez-Morales, Angel Jimenez-Fernandez, Ryad Benosman

In recent years tremendous efforts have been done to advance the state of the art for Natural Language Processing (NLP) and audio recognition.


Neutron-Induced, Single-Event Effects on Neuromorphic Event-based Vision Sensor: A First Step Towards Space Applications

no code implementations29 Jan 2021 Seth Roffe, Himanshu Akolkar, Alan D. George, Bernabé Linares-Barranco, Ryad Benosman

The results show that event-based cameras are capable of functioning in a space-like, radiative environment with a signal-to-noise ratio of 3. 355.

Event-based vision

Real-time high speed motion prediction using fast aperture-robust event-driven visual flow

no code implementations27 Nov 2018 Himanshu Akolkar, Sio-Hoi Ieng, Ryad Benosman

Optical flow is a crucial component of the feature space for early visual processing of dynamic scenes especially in new applications such as self-driving vehicles, drones and autonomous robots.

Motion Estimation motion prediction +1

Event-Based Features Selection and Tracking from Intertwined Estimation of Velocity and Generative Contours

no code implementations19 Nov 2018 Laurent Dardelet, Sio-Hoi Ieng, Ryad Benosman

This paper presents a new event-based method for detecting and tracking features from the output of an event-based camera.

Event-based Gesture Recognition with Dynamic Background Suppression using Smartphone Computational Capabilities

no code implementations19 Nov 2018 Jean-Matthieu Maro, Ryad Benosman

This paper introduces a framework of gesture recognition operating on the output of an event based camera using the computational resources of a mobile phone.

Gesture Recognition

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

no code implementations19 Nov 2018 Marco Macanovic, Fabian Chersi, Felix Rutard, Sio-Hoi Ieng, Ryad Benosman

We introduce in this paper 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.

BIG-bench Machine Learning

A Sparse Coding Multi-Scale Precise-Timing Machine Learning Algorithm for Neuromorphic Event-Based Sensors

no code implementations24 Apr 2018 Germain Haessig, Ryad Benosman

This paper introduces an unsupervised time-oriented event-based machine learning algorithm building on the concept of hierarchy of temporal descriptors called time surfaces.

BIG-bench Machine Learning

Event-based Face Detection and Tracking in the Blink of an Eye

no code implementations27 Mar 2018 Gregor Lenz, Sio-Hoi Ieng, Ryad Benosman

We will rely on a new feature that has never been used for such a task that relies on detecting eye blinks.

Face Detection

HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification

1 code implementation CVPR 2018 Amos Sironi, Manuele Brambilla, Nicolas Bourdis, Xavier Lagorce, Ryad Benosman

Compared to previous approaches, we use local memory units to efficiently leverage past temporal information and build a robust event-based representation.

Autonomous Vehicles Classification +2

HFirst: A Temporal Approach to Object Recognition

no code implementations5 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.

Object Recognition

STICK: Spike Time Interval Computational Kernel, A Framework for General Purpose Computation using Neurons, Precise Timing, Delays, and Synchrony

1 code implementation22 Jul 2015 Xavier Lagorce, Ryad Benosman

There has been significant research over the past two decades in developing new platforms for spiking neural computation.

Cannot find the paper you are looking for? You can Submit a new open access paper.