wasm-learning
neural-network-from-scratch
| wasm-learning | neural-network-from-scratch | |
|---|---|---|
| 5 | 3 | |
| 475 | 114 | |
| 0.8% | - | |
| 2.8 | 0.0 | |
| 2 months ago | about 2 years ago | |
| Rust | Rust | |
| - | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
wasm-learning
-
Can I rewrite my TypeScript library in Rust?
You could actually run wasm in both node and browser environments - then have your wrapper do any initialization based on the environment your library is in. This tutorial might help.
-
Starting to hate Tableau - any ideas for next moves?
Developers: Getting started building Rust + JavaScript hybrid apps for Node.js.
-
😎 Manage WebAssembly Apps in WasmEdge Using Docker Tools
The application source code is just a main.rs function. It is here. The application demonstrates how to access the file system and other operating system resources from WasmEdge using the standard Rust API.
- Creating Rust Functions in Node.js with SSVM and Docker
neural-network-from-scratch
- Examine individual neurons of a small neural network in the browser
-
Language models can explain neurons in language models
I built a toy neural network that runs in the browser[1] to model 2D functions with the goal of doing something similar to this research (in a much more limited manner, ofc). Since the input space is so much more limited than language models or similar, it's possible to examine the outputs for each neuron for all possible inputs, and in a continuous manner.
In some cases, you can clearly see neurons that specialize to different areas of the function being modeled, like this one: https://i.ameo.link/b0p.png
This OpenAI research seems to be feeding lots of varied input text into the models they're examining and keeping track of the activations of different neurons along the way. Another method I remember seeing used in the past involves using an optimizer to generate inputs that maximally activate particular neurons in vision models[2].
I'm sure that's much more difficult or even impossible for transformers which operate on sequences of tokens/embeddings rather than single static input vectors, but maybe there's a way to generate input embeddings and then use some method to convert them back into tokens.
[1] https://nn.ameo.dev/
[2] https://www.tensorflow.org/tutorials/generative/deepdream
-
Browser-based neural network sandbox built with Rust + WebAssembly
Full source code is on Github: https://github.com/ameobea/neural-network-from-scratch
What are some alternatives?
rustwasmc - Tool for building Rust functions for Node.js. Combine the performance of Rust, safety and portability of WebAssembly, and ease of use of JavaScript.
shorelark - Simulation of life & evolution
ssvm-nodejs-starter - A template project to run Rust functions in Node.js through the Second State WebAssembly engine.
wasm-pdf - Generate PDF files with JavaScript and WASM (WebAssembly)
Rust-Game-Template - Rust template for a 2d retro type game 🎉🕹
bhtsne - Parallel Barnes-Hut t-SNE implementation written in Rust.
nodejs-snowflake - Generate time sortable 64 bits unique ids for distributed systems (inspired from twitter snowflake)
Seed - A Rust framework for creating web apps
cri-o - Open Container Initiative-based implementation of Kubernetes Container Runtime Interface
minesweeper - Minesweeper game developed with Rust, WebAssembly (Wasm), and Canvas
runw
bitque - A simplified Jira clone built with seed.rs and actix