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

Deep Temporal Networks (DTNets) extend convolutional networks to incorporate large temporal windows, enabling efficient processing of both image and event-based data on conventional hardware inspired by brain integration principles.

Contribution

Introduction of Deep Temporal Networks that integrate spatial and temporal information, compatible with existing hardware and applicable to various data types.

Findings

Preliminary results demonstrate efficiency of DTNets.

Applicable to both conventional images and event-based data.

Operates on standard hardware without specialized neuromorphic chips.

Abstract

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. The concept can be used for conventional image inputs but also event based data. Although inspired by the architecture of brain that inegrates information over increasingly larger spatial but also temporal scales it can operate on conventional hardware using existing architectures. We introduce preliminary results to show the efficiency of the method. More in-depth results and analysis will be reported soon!