Suma G Cardwell
ABSTRACT
In this paper, we highlight how computational properties of biological dendrites can be leveraged for neuromorphic applications. Specifically, we demonstrate analog silicon dendrites that support multiplication mediated by conductance-based input in an interception model inspired by the biological dragonfly. We also demonstrate spatiotemporal pattern recognition and direction selectivity using dendrites on the Loihi neuromorphic platform. These dendritic circuits can be assembled hierarchically as building blocks for classifying complex spatiotemporal patterns.
- Jyotibdha Acharya, Arindam Basu, Robert Legenstein, Thomas Limbacher, Panayiota Poirazi, and Xundong Wu. 2022. Dendritic computing: branching deeper into machine learning. Neuroscience 489 (2022), 275--289.Google Scholar
Cross Ref
- Kwabena Boahen. 2022. Dendrocentric learning for synthetic intelligence. Nature 612, 7938 (2022), 43--50.Google Scholar
- Frances S Chance. 2020. Interception from a Dragonfly Neural Network Model. In International Conference on Neuromorphic Systems 2020. ACM, 1--5.Google ScholarDigital Library
- Frances S Chance and Suma G Cardwell. 2023. Shunting Inhibition as a Neural-Inspired Mechanism for Multiplication in Neuromorphic Architectures. In Neuro-Inspired Computational Elements Conference. ACM, San Antonio, 41--46.Google ScholarDigital Library
- Spyridon Chavlis and Panayiota Poirazi. 2021. Drawing inspiration from biological dendrites to empower artificial neural networks. Current opinion in neurobiology 70 (2021), 1--10.Google Scholar
- Mike Davies, Narayan Srinivasa, Tsung-Han Lin, Gautham Chinya, Yongqiang Cao, Sri Harsha Choday, Georgios Dimou, Prasad Joshi, Nabil Imam, Shweta Jain, et al. 2018. Loihi: A neuromorphic manycore processor with on-chip learning. Ieee Micro 38, 1 (2018), 82--99.Google ScholarCross Ref
- Guillermo Gallego, Tobi Delbrück, Garrick Orchard, Chiara Bartolozzi, Brian Taba, Andrea Censi, Stefan Leutenegger, Andrew J Davison, Jörg Conradt, Kostas Daniilidis, et al. 2020. Event-based vision: A survey. IEEE transactions on pattern analysis and machine intelligence 44, 1 (2020), 154--180.Google Scholar
- Suma George, Jennifer Hasler, Scott Koziol, Stephen Nease, and Shubha Ramakrishnan. 2013. Low power dendritic computation for wordspotting. Journal of Low Power Electronics and Applications 3, 2 (2013), 73--98.Google ScholarCross Ref
- Suma George, Sihwan Kim, Sahil Shah, Jennifer Hasler, Michelle Collins, Farhan Adil, Richard Wunderlich, Stephen Nease, and Shubha Ramakrishnan. 2016. A programmable and configurable mixed-mode FPAA SoC. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 24, 6 (2016), 2253--2261.Google ScholarDigital Library
- Lukas N Groschner, Jonatan G Malis, Birte Zuidinga, and Alexander Borst. 2022. A biophysical account of multiplication by a single neuron. Nature 603, 7899 (2022), 119--123.Google Scholar
- Abhiram Iyer, Karan Grewal, Akash Velu, Lucas Oliveira Souza, Jeremy Forest, and Subutai Ahmad. 2022. Avoiding catastrophe: Active dendrites enable multitask learning in dynamic environments. Frontiers in neurorobotics 16 (2022), 846219.Google Scholar
- Jakob Kaiser, Sebastian Billaudelle, Eric Müller, Christian Tetzlaff, Johannes Schemmel, and Sebastian Schmitt. 2022. Emulating dendritic computing paradigms on analog neuromorphic hardware. Neuroscience 489 (2022), 290--300.Google Scholar
- Yann LeCun, Yoshua Bengio, et al. 1995. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks 3361, 10 (1995), 1995.Google Scholar
- Xinyi Li, Jianshi Tang, Qingtian Zhang, Bin Gao, J Joshua Yang, Sen Song, Wei Wu, Wenqiang Zhang, Peng Yao, Ning Deng, et al. 2020. Power-efficient neural network with artificial dendrites. Nature Nanotechnology 15, 9 (2020), 776--782.Google ScholarCross Ref
- Michael London and Michael Häusser. 2005. Dendritic computation. Annu. Rev. Neurosci. 28 (2005), 503--532.Google ScholarCross Ref
- Jenny Lu, Amir H Behbahani, Lydia Hamburg, Elena A Westeinde, Paul M Dawson, Cheng Lyu, Gaby Maimon, Michael H Dickinson, Shaul Druckmann, and Rachel I Wilson. 2022. Transforming representations of movement from body-to world-centric space. Nature 601, 7891 (2022), 98--104.Google Scholar
- Cheng Lyu, LF Abbott, and Gaby Maimon. 2022. Building an allocentric travelling direction signal via vector computation. Nature 601, 7891 (2022), 92--97.Google Scholar
- Stephen Nease, Suma George, Paul Hasler, Scott Koziol, and Stephen Brink. 2011. Modeling and implementation of voltage-mode CMOS dendrites on a reconfigurable analog platform. IEEE transactions on biomedical circuits and systems 6, 1 (2011), 76--84.Google Scholar
- Shubha Ramakrishnan, Richard Wunderlich, Jennifer Hasler, and Suma George. 2013. Neuron array with plastic synapses and programmable dendrites. IEEE transactions on biomedical circuits and systems 7, 5 (2013), 631--642.Google ScholarCross Ref
- Frank Rosenblatt. 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review 65, 6 (1958), 386.Google Scholar
- Arnob Saha, ANM Nafiul Islam, Zijian Zhao, Shan Deng, Kai Ni, and Abhronil Sengupta. 2021. Intrinsic synaptic plasticity of ferroelectric field effect transistors for online learning. Applied Physics Letters 119, 13 (2021), 133701.Google ScholarCross Ref
- Emilio Salinas and Larry F Abbott. 1995. Transfer of coded information from sensory to motor networks. Journal of Neuroscience 15, 10 (1995), 6461--6474.Google ScholarCross Ref
- Johannes Schemmel, Laura Kriener, Paul Müller, and Karlheinz Meier. 2017. An accelerated analog neuromorphic hardware system emulating NMDA-and calcium-based non-linear dendrites. In 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, 2217--2226.Google ScholarCross Ref
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1 (2014), 1929--1958.Google ScholarDigital Library
- Scott T Steinmetz, Oliver W Layton, Nathaniel V Powell, and Brett R Fajen. 2022. A dynamic efficient sensory encoding approach to adaptive tuning in neural models of optic flow processing. Frontiers in computational neuroscience 16 (2022), 844289.Google Scholar
Index Terms
- Dendritic Computation for Neuromorphic Applications
Recommendations
Shunting Inhibition as a Neural-Inspired Mechanism for Multiplication in Neuromorphic Architectures
NICE '23: Proceedings of the 2023 Annual Neuro-Inspired Computational Elements ConferenceShunting inhibition is a potential mechanism by which biological systems multiply two time-varying signals, most recently proposed in single neurons of the fly visual system. Our work demonstrates this effect in a biological neuron model and the ...
Dendritic Computation in a Point Neuron Model
Artificial Neural Networks and Machine Learning – ICANN 2020AbstractBiological neurons possess elaborate dendrites that perform elaborate computations. They are however ignored in the widely used point neuron models. Here, we present a simple addition to the commonly used leaky integrate-and-fire model that ...
Effects of Noise on Leaky Integrate-and-Fire Neuron Models for Neuromorphic Computing Applications
Computational Science and Its Applications – ICCSA 2022AbstractArtificial neural networks (ANNs) have been extensively used for the description of problems arising from biological systems and for constructing neuromorphic computing models. The third generation of ANNs, namely, spiking neural networks (SNNs), ...
Comments