Skip to content

Commit 4185220

Browse files
committed
docs: Improve internal resource linking
1 parent f91a677 commit 4185220

File tree

6 files changed

+6
-6
lines changed
  • content
    • blog
      • open-neuromorphic-evolves-charter-first-executive-committee-election
      • spiking-neural-network-framework-benchmarking
      • strategic-vision-open-neuromorphic
    • contributors
    • getting-involved

6 files changed

+6
-6
lines changed

content/blog/open-neuromorphic-evolves-charter-first-executive-committee-election/index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -55,6 +55,6 @@ Can't make it? You can transfer your vote to another attending member. Details o
5555

5656
## Get Involved!
5757

58-
This is a significant milestone for Open Neuromorphic, driven by our commitment to building a sustainable and impactful open-source community. Your participation is vital! Please review the charter, consider running for a position, and plan to attend the AGM to cast your vote.
58+
This is a significant milestone for Open Neuromorphic, driven by our commitment to building a sustainable and impactful open-source community. Your participation is vital! Please review the charter, consider running for a position, and plan to attend the AGM to cast your vote on the [Executive Committee](/neuromorphic-computing/initiatives/executive-committee/).
5959

6060
Let's shape the future of ONM together!

content/blog/spiking-neural-network-framework-benchmarking/index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ show_author_bios: true
1818

1919
## Introduction
2020

21-
Open Neuromorphic's [list of SNN frameworks](https://github.com/open-neuromorphic/open-neuromorphic) currently counts 11 libraries, and those are only the most popular ones! As the sizes of [spiking neural network models](/neuromorphic-computing/software/snn-frameworks/) grow thanks to deep learning, optimization becomes more important for researchers and practitioners alike. Training SNNs is often slow, as the stateful networks are typically fed sequential inputs. Today's most popular training method then is some form of backpropagation through time, whose time complexity scales with the number of time steps. We benchmark libraries that all take slightly different approaches on how to extend deep learning frameworks for gradient-based optimization of SNNs. We focus on the total time it takes to pass data forward and backward through the network as well as the memory required to do so. However, there are obviously other, non-tangible qualities of frameworks such as extensibility, quality of documentation, ease of install or support for neuromorphic hardware that we're not going to try to capture here. In our benchmarks, we use a single fully-connected (linear) and a leaky integrate and fire (LIF) layer. The input data has batch size of 16, 500 time steps and n neurons.
21+
Open Neuromorphic's [SNN frameworks guide](/neuromorphic-computing/software/snn-frameworks/) currently counts 11 libraries, and those are only the most popular ones! As the sizes of [spiking neural network models](/neuromorphic-computing/software/snn-frameworks/) grow thanks to deep learning, optimization becomes more important for researchers and practitioners alike. Training SNNs is often slow, as the stateful networks are typically fed sequential inputs. Today's most popular training method then is some form of backpropagation through time, whose time complexity scales with the number of time steps. We benchmark libraries that all take slightly different approaches on how to extend deep learning frameworks for gradient-based optimization of SNNs. We focus on the total time it takes to pass data forward and backward through the network as well as the memory required to do so. However, there are obviously other, non-tangible qualities of frameworks such as extensibility, quality of documentation, ease of install or support for neuromorphic hardware that we're not going to try to capture here. In our benchmarks, we use a single fully-connected (linear) and a leaky integrate and fire (LIF) layer. The input data has batch size of 16, 500 time steps and n neurons.
2222

2323
## Benchmark Results
2424

content/blog/strategic-vision-open-neuromorphic/index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ show_author_bios: true
2020

2121
This post presents a **vision for Open Neuromorphic** towards more open, reproducible, and competitive neuromorphics.
2222

23-
The post will be the first in a series that lays out the **Open Neuromorphic Strategic Initiative** where we later discuss **Neuromorphic UX** and **new initiatives** that will be kickstarted by the [newly elected Executive Committee](/blog/open-neuromorphic-evolves-charter-first-executive-committee-election/).
23+
The post will be the first in a series that lays out the **Open Neuromorphic Strategic Initiative** where we later discuss **Neuromorphic UX** and **new initiatives** that will be kickstarted by the [newly elected Executive Committee](/neuromorphic-computing/initiatives/executive-committee/).
2424

2525
Join the discussion [on Discord](https://discord.gg/hUygPUdD8E), star us [on GitHub](https://github.com/open-neuromorphic/), follow us [on LinkedIn](https://www.linkedin.com/company/98345683/), and give us a watch [on YouTube](https://www.youtube.com/@openneuromorphic).
2626

content/contributors/jens-e-pedersen/index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,4 +25,4 @@ vision, motor control, and self-sustenance, Jens seeks to build autonomous syste
2525
that perform meaningful work, tightly following the Feynman axiom ''What I cannot
2626
create, I do not understand''.
2727

28-
He is the maintainer of [norse](https://github.com/norse/norse) and [AEStream](https:github.com/norse/aestream).
28+
He is the maintainer of [norse](/neuromorphic-computing/software/snn-frameworks/norse/) and [AEStream](/neuromorphic-computing/software/data-tools/aestream/).

content/contributors/justin-riddiough/index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,6 @@ draft: false
1616
---
1717
Justin Riddiough is a strategic digital solutions partner and dedicated open-source advocate. As the Vice-Chair of the Open Neuromorphic Executive Committee, he plays a key role in shaping the community's growth and digital strategy.
1818

19-
He designed and built the Open Neuromorphic website, creating the central hub for our resources, events, and community engagement.
19+
He designed and built the [Open Neuromorphic website](/), creating the central hub for our resources, events, and community engagement.
2020

2121
With over two decades of experience deploying robust, scalable web applications, Justin brings a wealth of technical and strategic knowledge to the team. He is a strong proponent of connectivism, applying its principles of networked learning to help build a collaborative and accessible ecosystem for neuromorphic computing. His work focuses on creating powerful digital tools and coordinating growth across open-source initiatives to empower communities and advance shared knowledge.

content/getting-involved/_index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -59,6 +59,6 @@ Collaborate on community-driven projects that shape the future of ONM. Explore e
5959
{{< /contribution_card >}}
6060
</div>
6161

62-
Beyond these pathways, a quick and easy way to support our community is by sharing our [website](https://open-neuromorphic.org/) and [Discord](https://discord.gg/hUygPUdD8E) with your friends and colleagues. We're always looking for new members, and linking to our site helps boost our search engine rankings, making it easier for others to find us.
62+
Beyond these pathways, a quick and easy way to support our community is by sharing our [website](/) and [Discord](https://discord.gg/hUygPUdD8E) with your friends and colleagues. We're always looking for new members, and linking to our site helps boost our search engine rankings, making it easier for others to find us.
6363

6464
If you're new, we recommend joining our [Discord](https://discord.gg/hUygPUdD8E) to connect with other members. Leave a message in the `#welcome` channel to introduce yourself!

0 commit comments

Comments
 (0)