2000 character limit reached
Learning with Chemical versus Electrical Synapses -- Does it Make a Difference? (2401.08602v1)
Published 21 Nov 2023 in cs.NE and cs.LG
Abstract: Bio-inspired neural networks have the potential to advance our understanding of neural computation and improve the state-of-the-art of AI systems. Bio-electrical synapses directly transmit neural signals, by enabling fast current flow between neurons. In contrast, bio-chemical synapses transmit neural signals indirectly, through neurotransmitters. Prior work showed that interpretable dynamics for complex robotic control, can be achieved by using chemical synapses, within a sparse, bio-inspired architecture, called Neural Circuit Policies (NCPs). However, a comparison of these two synaptic models, within the same architecture, remains an unexplored area. In this work we aim to determine the impact of using chemical synapses compared to electrical synapses, in both sparse and all-to-all connected networks. We conduct experiments with autonomous lane-keeping through a photorealistic autonomous driving simulator to evaluate their performance under diverse conditions and in the presence of noise. The experiments highlight the substantial influence of the architectural and synaptic-model choices, respectively. Our results show that employing chemical synapses yields noticeable improvements compared to electrical synapses, and that NCPs lead to better results in both synaptic models.
- R. D. Beer and J. C. Gallagher, “Evolving dynamical neural networks for adaptive behavior,” Adaptive behavior, vol. 1, no. 1, pp. 91–122, 1992.
- K. Funahashi and Y. Nakamura, “Approximation of dynamical systems by continuous time recurrent neural networks,” Neural Networks, vol. 6, pp. 801–806, 1993.
- R. T. Q. Chen, Y. Rubanova, J. Bettencourt, and D. K. Duvenaud, “Neural ordinary differential equations,” in Advances in Neural Information Processing Systems, vol. 31, pp. 1–13, Curran Associates, Inc., 2018.
- R. M. Hasani, M. Lechner, A. Amini, D. Rus, and R. Grosu, “Liquid time-constant networks,” in AAAI Conference on Artificial Intelligence, 2020.
- M. Lechner, R. M. Hasani, A. Amini, T. A. Henzinger, D. Rus, and R. Grosu, “Neural circuit policies enabling auditable autonomy,” Nature Machine Intelligence, vol. 2, pp. 642–652, 2020.
- C. J. Vorbach, R. M. Hasani, A. Amini, M. Lechner, and D. Rus, “Causal navigation by continuous-time neural networks,” in Neural Information Processing Systems, 2021.
- M. Chahine, R. Hasani, P. Kao, A. Ray, R. Shubert, M. Lechner, A. Amini, and D. Rus, “Robust flight navigation out of distribution with liquid neural networks,” Science Robotics, vol. 8, no. 77, p. eadc8892, 2023.
- M. Lechner, R. Hasani, M. Zimmer, T. A. Henzinger, and R. Grosu, “Designing worm-inspired neural networks for interpretable robotic control,” in 2019 International Conference on Robotics and Automation (ICRA), pp. 87–94, 2019.
- G.-B. Zhou, J. Wu, C.-L. Zhang, and Z.-H. Zhou, “Minimal gated unit for recurrent neural networks,” 2016.
- S. Schaal, “Is imitation learning the route to humanoid robots?,” Trends in Cognitive Sciences, vol. 3, pp. 233–242, 1999.
- A. Amini, T.-H. Wang, I. Gilitschenski, W. Schwarting, Z. Liu, S. Han, S. Karaman, and D. Rus, “Vista 2.0: An open, data-driven simulator for multimodal sensing and policy learning for autonomous vehicles,” in 2022 International Conference on Robotics and Automation (ICRA), pp. 2419–2426, IEEE, 2022.
- S. R. Wicks, C. J. Roehrig, and C. H. Rankin, “A dynamic network simulation of the nematode tap withdrawal circuit: predictions concerning synaptic function using behavioral criteria,” Journal of Neuroscience, vol. 16, no. 12, pp. 4017–4031, 1996.
- McGraw-hill New York, 2000.
- E. Johns, “Coarse-to-fine imitation learning: Robot manipulation from a single demonstration,” in 2021 IEEE international conference on robotics and automation (ICRA), pp. 4613–4619, IEEE, 2021.
- X. B. Peng, E. Coumans, T. Zhang, T.-W. Lee, J. Tan, and S. Levine, “Learning agile robotic locomotion skills by imitating animals,” arXiv preprint arXiv:2004.00784, 2020.
- H. Karnan, G. Warnell, X. Xiao, and P. Stone, “Voila: Visual-observation-only imitation learning for autonomous navigation,” in 2022 International Conference on Robotics and Automation (ICRA), pp. 2497–2503, IEEE, 2022.
- Y. Fan, S. Chu, W. Zhang, R. Song, and Y. Li, “Learn by observation: Imitation learning for drone patrolling from videos of a human navigator,” in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5209–5216, IEEE, 2020.
- M. Bojarski, D. W. del Testa, D. Dworakowski, B. Firner, B. Flepp, P. Goyal, L. D. Jackel, M. Monfort, U. Muller, J. Zhang, X. Zhang, J. Zhao, and K. Zieba, “End to end learning for self-driving cars,” ArXiv, vol. abs/1604.07316, 2016.
- H. Xu, Y. Gao, F. Yu, and T. Darrell, “End-to-end learning of driving models from large-scale video datasets,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3530–3538, 2016.
- R. D. Beer, “A dynamical systems perspective on agent-environment interaction,” Artificial intelligence, vol. 72, no. 1-2, pp. 173–215, 1995.
- H. Tang, B. H. Tan, and R. Yan, “Robot-to-human handover with obstacle avoidance via continuous time recurrent neural network,” in 2016 IEEE Congress on Evolutionary Computation (CEC), pp. 1204–1211, 2016.
- P. Hénaff, V. Scesa, F. B. Ouezdou, and O. Bruneau, “Real time implementation of ctrnn and bptt algorithm to learn on-line biped robot balance: Experiments on the standing posture,” ArXiv, vol. abs/2011.06910, 2020.
- R. Sendra-Arranz and Á. Gutiérrez, “Emergence of communication through artificial evolution in an orientation consensus task in swarm robotics,” in IFIP International Conference on Artificial Intelligence Applications and Innovations, pp. 515–526, Springer, 2023.
- S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.
- F. Codevilla, A. M. Lopez, V. Koltun, and A. Dosovitskiy, “On offline evaluation of vision-based driving models,” in Proceedings of the European Conference on Computer Vision (ECCV), pp. 236–251, 2018.
- M. Bojarski, A. Choromańska, K. Choromanski, B. Firner, L. D. Jackel, U. Muller, and K. Zieba, “Visualbackprop: visualizing cnns for autonomous driving,” ArXiv, vol. abs/1611.05418, 2016.
- Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004.
- M. Lechner, R. Hasani, A. Amini, T.-H. Wang, T. A. Henzinger, and D. Rus, “Are all vision models created equal? a study of the open-loop to closed-loop causality gap,” arXiv preprint arXiv:2210.04303, 2022.
- S. Levine and V. Koltun, “Guided policy search,” in Proceedings of the 30th International Conference on Machine Learning (S. Dasgupta and D. McAllester, eds.), vol. 28 of Proceedings of Machine Learning Research, (Atlanta, Georgia, USA), pp. 1–9, PMLR, 17–19 Jun 2013.
- A. Amini, I. Gilitschenski, J. Phillips, J. Moseyko, R. Banerjee, S. Karaman, and D. Rus, “Learning robust control policies for end-to-end autonomous driving from data-driven simulation,” IEEE Robotics and Automation Letters, vol. 5, pp. 1143–1150, 2020.
- I. Loshchilov and F. Hutter, “Fixing weight decay regularization in adam,” ArXiv, vol. abs/1711.05101, 2017.
- A. Power, Y. Burda, H. Edwards, I. Babuschkin, and V. Misra, “Grokking: Generalization beyond overfitting on small algorithmic datasets,” ArXiv, vol. abs/2201.02177, 2022.