Timezone: »
We propose a neural information processing system obtained by re-purposing the function of a biological neural circuit model to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce ordinary neural circuits (ONCs), defined as the model of biological neural circuits reparameterized for the control of alternative tasks. We first demonstrate that ONCs realize networks with higher maximum flow compared to arbitrary wired networks. We then learn instances of ONCs to control a series of robotic tasks, including the autonomous parking of a real-world rover robot. For reconfiguration of the purpose of the neural circuit, we adopt a search-based optimization algorithm. Ordinary neural circuits perform on par and, in some cases, significantly surpass the performance of contemporary deep learning models. ONC networks are compact, 77% sparser than their counterpart neural controllers, and their neural dynamics are fully interpretable at the cell-level.
Author Information
Ramin Hasani (MIT)
Mathias Lechner (IST Austria)
Alexander Amini (MIT)
Daniela Rus (MIT CSAIL)
Radu Grosu (TU Wien)
More from the Same Authors
-
2021 : Is Bang-Bang Control All You Need? »
Tim Seyde · Igor Gilitschenski · Wilko Schwarting · Bartolomeo Stellato · Martin Riedmiller · Markus Wulfmeier · Daniela Rus -
2021 : Invited Talk 2: Addressing Model Bias and Uncertainty via Evidential Deep Learning »
Daniela Rus -
2021 Poster: The Logical Options Framework »
Brandon Araki · Xiao Li · Kiran Vodrahalli · Jonathan DeCastro · Micah Fry · Daniela Rus -
2021 Poster: On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification »
Zahra Babaiee · Ramin Hasani · Mathias Lechner · Daniela Rus · Radu Grosu -
2021 Spotlight: On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification »
Zahra Babaiee · Ramin Hasani · Mathias Lechner · Daniela Rus · Radu Grosu -
2021 Oral: The Logical Options Framework »
Brandon Araki · Xiao Li · Kiran Vodrahalli · Jonathan DeCastro · Micah Fry · Daniela Rus -
2020 Poster: Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control »
Jie Xu · Yunsheng Tian · Pingchuan Ma · Daniela Rus · Shinjiro Sueda · Wojciech Matusik -
2019 : Alexander Amini: "Learning to Drive with Purpose" »
Alexander Amini -
2019 : posters »
Zhengxing Chen · Juan Jose Garau Luis · Ignacio Albert Smet · Aditya Modi · Sabina Tomkins · Riley Simmons-Edler · Hongzi Mao · Alexander Irpan · Hao Lu · Rose Wang · Subhojyoti Mukherjee · Aniruddh Raghu · Syed Arbab Mohd Shihab · Byung Hoon Ahn · Rasool Fakoor · Pratik Chaudhari · Elena Smirnova · Min-hwan Oh · Xiaocheng Tang · Tony Qin · Qingyang Li · Marc Brittain · Ian Fox · Supratik Paul · Xiaofeng Gao · Yinlam Chow · Gabriel Dulac-Arnold · Ofir Nachum · Nikos Karampatziakis · Bharathan Balaji · Supratik Paul · Ali Davody · Djallel Bouneffouf · Himanshu Sahni · Soo Kim · Andrey Kolobov · Alexander Amini · Yao Liu · Xinshi Chen · · Craig Boutilier -
2017 Poster: Coresets for Vector Summarization with Applications to Network Graphs »
Dan Feldman · Sedat Ozer · Daniela Rus -
2017 Talk: Coresets for Vector Summarization with Applications to Network Graphs »
Dan Feldman · Sedat Ozer · Daniela Rus