https://arxiv.org/abs/2009.06808
Short-term synaptic plasticity optimally models continuous environments
Timoleon Moraitis, Abu Sebastian, Evangelos Eleftheriou (IBM Research - Zurich)
Biological neural networks operate with extraordinary energy efficiency, owing to properties such as spike-based communication and synaptic plasticity driven by local activity. When emulated in silico, such properties also enable highly energy-efficient machine learning and inference systems. However, it is unclear whether these mechanisms only trade off performance for efficiency or rather they are partly responsible for the superiority of biological intelligence. Here, we first address this theoretically, proving rigorously that indeed the optimal prediction and inference of randomly but continuously transforming environments, a common natural setting, relies on adaptivity through short-term spike-timing dependent plasticity, a hallmark of biological neural networks. Secondly, we assess this theoretical optimality via simulations and also demonstrate improved artificial intelligence (AI). For the first time, a largely biologically modelled spiking neural network (SNN) surpasses state-of-the-art artificial neural networks (ANNs) in all relevant aspects, in an example task of recognizing video frames transformed by moving occlusions. The SNN recognizes the frames more accurately, even if trained on few, still, and untransformed images, with unsupervised and synaptically-local learning, binary spikes, and a single layer of neurons - all in contrast to the deep-learning-trained ANNs. These results indicate that on-line adaptivity and spike-based computation may optimize natural intelligence for natural environments. Moreover, this expands the goal of exploiting biological neuro-synaptic properties for AI, from mere efficiency, to computational supremacy altogether.
don't let the pig gas light you
- Forums
- ASX - By Stock
- BRN
- Short-term synaptic plasticity optimally models continuous environments
Short-term synaptic plasticity optimally models continuous environments
-
- There are more pages in this discussion • 131 more messages in this thread...
You’re viewing a single post only. To view the entire thread just sign in or Join Now (FREE)
Featured News
Add BRN (ASX) to my watchlist
|
|||||
Last
22.0¢ |
Change
0.005(2.33%) |
Mkt cap ! $408.3M |
Open | High | Low | Value | Volume |
21.5¢ | 23.5¢ | 21.3¢ | $7.637M | 34.28M |
Buyers (Bids)
No. | Vol. | Price($) |
---|---|---|
15 | 503753 | 22.0¢ |
Sellers (Offers)
Price($) | Vol. | No. |
---|---|---|
23.0¢ | 196385 | 4 |
View Market Depth
No. | Vol. | Price($) |
---|---|---|
10 | 284840 | 0.220 |
22 | 562480 | 0.215 |
29 | 755011 | 0.210 |
28 | 767031 | 0.205 |
80 | 1789790 | 0.200 |
Price($) | Vol. | No. |
---|---|---|
0.230 | 12266 | 1 |
0.235 | 525889 | 15 |
0.240 | 474338 | 13 |
0.245 | 649877 | 14 |
0.250 | 332099 | 20 |
Last trade - 16.10pm 21/06/2024 (20 minute delay) ? |
Featured News
BRN (ASX) Chart |
The Watchlist
FHE
FRONTIER ENERGY LIMITED
Adam Kiley, CEO
Adam Kiley
CEO
SPONSORED BY The Market Online