Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity
Dec 6, 2021
Speakers
Vladimir Ivanov
Speaker · 0 followers
Konstantinos Michmizos
Speaker · 0 followers
About
The liquid state machine (LSM) combines low training complexity and biological plausibility, which has made it an attractive machine learning framework for edge and neuromorphic computing paradigms. Originally proposed as a model of brain computation, the LSM tunes its internal weights without backpropagation of gradients, which results in lower performance compared to multi-layer neural networks. Recent findings in neuroscience suggest that astrocytes, a long-neglected non-neuronal brain cell, modulate synaptic plasticity and brain dynamics, tuning brain networks into the computationally optimal critical phase transition between order and chaos. Inspired by this disruptive understanding of how brain networks self-tune, we propose the neuron-astrocyte liquid state machine (NALSM) that addresses under-performance through self-organized critical dynamics. Similar to its biological counterpart, the astrocyte model integrates neuronal activity and provides global feedback to spike-timing-dependent plasticity (STDP), which self-organizes NALSM dynamics at the edge-of-chaos. We demonstrate that NALSM achieves state-of-the-art accuracy versus comparable LSM methods, without the need for data-specific hand-tuning. With a top accuracy of 97.61% on MNIST and 97.51% on N-MNIST, NALSM achieved comparable performance to current fully-connected multi-layer spiking neural networks trained via backpropagation. Our findings suggest that the further development of brain-inspired machine learning methods has the potential to reach the performance of deep learning, with the added benefits of supporting robust and energy-efficient neuromorphic computing on the edge.The liquid state machine (LSM) combines low training complexity and biological plausibility, which has made it an attractive machine learning framework for edge and neuromorphic computing paradigms. Originally proposed as a model of brain computation, the LSM tunes its internal weights without backpropagation of gradients, which results in lower performance compared to multi-layer neural networks. Recent findings in neuroscience suggest that astrocytes, a long-neglected non-neuronal brain cell,…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Advanced Topics in Model Predictive Control
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Adversarial Feature Desensitization
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Unsupervised Spectral Unmixing for Telluric Correction using a Neural Network Autoencoder
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Classifying Anomalies THrough Outer Density Estimation (CATHODE)
Watch later
Anna Halin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Greedy Approximation Algorithms for Active Sequential Hypothesis Testing
Watch later
Kyra Gan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
H+AI:: Exploring the Dark Side of Human-AI Interaction
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%