Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@andycarolan@social.lol
2024-03-28 13:17:08

Working closely with a wide range of companies, I have developed logos, logotypes, and symbols that are true representations of each brand, complement their particular fields, and resonate with the audience they hope to reach.
andycarolan.com/work/logofolio

@UP8@mastodon.social
2024-04-17 20:33:24

đź“– To Make Unions Resonate Again, Study the CIO’s History
#labor

@arXiv_csNE_bot@mastoxiv.page
2024-02-23 06:51:21

Balanced Resonate-and-Fire Neurons
Saya Higuchi, Sebastian Kairat, Sander M. Bohte. Sebastian Otte
arxiv.org/abs/2402.14603 arxiv.org/pdf/2402.14603
arXiv:2402.14603v1 Announce Type: new
Abstract: The resonate-and-fire (RF) neuron, introduced over two decades ago, is a simple, efficient, yet biologically plausible spiking neuron model, which can extract frequency patterns within the time domain due to its resonating membrane dynamics. However, previous RF formulations suffer from intrinsic shortcomings that limit effective learning and prevent exploiting the principled advantage of RF neurons. Here, we introduce the balanced RF (BRF) neuron, which alleviates some of the intrinsic limitations of vanilla RF neurons and demonstrates its effectiveness within recurrent spiking neural networks (RSNNs) on various sequence learning tasks. We show that networks of BRF neurons achieve overall higher task performance, produce only a fraction of the spikes, and require significantly fewer parameters as compared to modern RSNNs. Moreover, BRF-RSNN consistently provide much faster and more stable training convergence, even when bridging many hundreds of time steps during backpropagation through time (BPTT). These results underscore that our BRF-RSNN is a strong candidate for future large-scale RSNN architectures, further lines of research in SNN methodology, and more efficient hardware implementations.

@claeculus@blorbo.social
2024-03-29 18:42:24

This slipped my mind, but there's something that crossed my mind after Main Story III.2 about Kamlanage. #clae_ae
What if Kamlanage, too, just like Aldo, is also "Another Eden"? Specifically, the supposed Eden of the Hollow Time Layer?
Although Ashtear said that Eden was never born in Hollow Time Layer (and he seems to be closer to Feinne in terms of appearance), Kamlanage's situation and designation is similar to Eden still. It may also explain to some degree why he can resonate with Feinne.

@gray17@mastodon.social
2024-03-23 18:35:25

today is taking a break from twine porn to resurrect a non-kinky non-furry story that I outlined several years ago but never finished drafting. it's now a little late, it might have landed better years ago, but it still feels like it might resonate in the moment, and it keeps nagging at me, so I might as well finish it and see if anyone else likes it

@andycarolan@social.lol
2024-03-19 11:20:23

In close partnership with a wide range of companies, I have developed logos, logotypes, and symbols that are true representations of that companies' brands, complement their particular fields, and resonate with the audiences they hope to reach.
#branding #logo

@cowboys@darktundra.xyz
2024-04-26 18:29:25

Legendary NFL Coach Sends Bold Message To Dallas Cowboys yardbarker.com/nfl/articles/le

@arXiv_csAI_bot@mastoxiv.page
2024-04-22 06:46:45

Food Development through Co-creation with AI: bread with a "taste of love"
Takuya Sera, Izumi Kuwata, Yuki Taya, Noritaka Shimura, Yosuke Motohashi
arxiv.org/abs/2404.12760

@arXiv_csNE_bot@mastoxiv.page
2024-02-23 06:51:21

Balanced Resonate-and-Fire Neurons
Saya Higuchi, Sebastian Kairat, Sander M. Bohte. Sebastian Otte
arxiv.org/abs/2402.14603 arxiv.org/pdf/2402.14603
arXiv:2402.14603v1 Announce Type: new
Abstract: The resonate-and-fire (RF) neuron, introduced over two decades ago, is a simple, efficient, yet biologically plausible spiking neuron model, which can extract frequency patterns within the time domain due to its resonating membrane dynamics. However, previous RF formulations suffer from intrinsic shortcomings that limit effective learning and prevent exploiting the principled advantage of RF neurons. Here, we introduce the balanced RF (BRF) neuron, which alleviates some of the intrinsic limitations of vanilla RF neurons and demonstrates its effectiveness within recurrent spiking neural networks (RSNNs) on various sequence learning tasks. We show that networks of BRF neurons achieve overall higher task performance, produce only a fraction of the spikes, and require significantly fewer parameters as compared to modern RSNNs. Moreover, BRF-RSNN consistently provide much faster and more stable training convergence, even when bridging many hundreds of time steps during backpropagation through time (BPTT). These results underscore that our BRF-RSNN is a strong candidate for future large-scale RSNN architectures, further lines of research in SNN methodology, and more efficient hardware implementations.

@andycarolan@social.lol
2024-04-15 19:34:32

Working closely with a wide range of companies, I have developed logos, logotypes, and symbols that are true representations of each brand, complement their particular fields, and resonate with the audience they hope to reach.
andycarolan.com/work/logofolio