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
This work addresses the need for time-aware machine learning models in neuromorphic engineering, though it appears incremental as it builds on existing convolutional network architectures.
The paper tackles the problem of integrating temporal information into convolutional networks for both conventional image and event-based data, introducing Deep Temporal Networks (DTNets) that operate on existing hardware and showing preliminary results of its efficiency.
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!