Vision-based route following by an embodied insect-inspired sparse neural network

Lu Yihe; Rana Alkhoury Maroun; Barbara Webb

Vision-based route following by an embodied insect-inspired sparse neural network

Lu Yihe
, Rana Alkhoury Maroun
, Barbara Webb

Research output: Working paper › Preprint

Abstract

We compared the efficiency of the FlyHash model, an insect-inspired sparse neural network (Dasgupta et al., 2017), to similar but non-sparse models in an embodied navigation task. This requires a model to control steering by comparing current visual inputs to memories stored along a training route. We concluded the FlyHash model is more efficient than others, especially in terms of data encoding.

Original language	English
Publisher	ArXiv
Pages	1-8
Number of pages	8
Publication status	Published - 14 Mar 2023

Keywords / Materials (for Non-textual outputs)

neural and evolutionary computing
machine learning
robotics

Access to Document

YiheEtalArXiv2023Vision-basedRouteFollowingSubmitted manuscript, 612 KBLicence: Creative Commons: Attribution-ShareAlike (CC-BY-SA)

Cite this

@techreport{b33a6b55c0e94afb81db63888aedd5c0,

title = "Vision-based route following by an embodied insect-inspired sparse neural network",

abstract = "We compared the efficiency of the FlyHash model, an insect-inspired sparse neural network (Dasgupta et al., 2017), to similar but non-sparse models in an embodied navigation task. This requires a model to control steering by comparing current visual inputs to memories stored along a training route. We concluded the FlyHash model is more efficient than others, especially in terms of data encoding.",

keywords = "neural and evolutionary computing, machine learning, robotics",

author = "Lu Yihe and \{Alkhoury Maroun\}, Rana and Barbara Webb",

year = "2023",

month = mar,

day = "14",

language = "English",

pages = "1--8",

publisher = "ArXiv",

type = "WorkingPaper",

institution = "ArXiv",

}

TY - UNPB

T1 - Vision-based route following by an embodied insect-inspired sparse neural network

AU - Yihe, Lu

AU - Alkhoury Maroun, Rana

AU - Webb, Barbara

PY - 2023/3/14

Y1 - 2023/3/14

N2 - We compared the efficiency of the FlyHash model, an insect-inspired sparse neural network (Dasgupta et al., 2017), to similar but non-sparse models in an embodied navigation task. This requires a model to control steering by comparing current visual inputs to memories stored along a training route. We concluded the FlyHash model is more efficient than others, especially in terms of data encoding.

AB - We compared the efficiency of the FlyHash model, an insect-inspired sparse neural network (Dasgupta et al., 2017), to similar but non-sparse models in an embodied navigation task. This requires a model to control steering by comparing current visual inputs to memories stored along a training route. We concluded the FlyHash model is more efficient than others, especially in terms of data encoding.

KW - neural and evolutionary computing

KW - machine learning

KW - robotics

M3 - Preprint

SP - 1

EP - 8

BT - Vision-based route following by an embodied insect-inspired sparse neural network

PB - ArXiv

ER -

Vision-based route following by an embodied insect-inspired sparse neural network

Abstract

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this