Neural Network Evolution Playground with Backprop NEAT
Neural Network Evolution Playground with Backprop NEAT launched on May 14, 2016 with 73 votes, #764 of 3,824 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 10 years on.
In plain words
Neural Network Evolution Playground with Backprop NEAT uses a genetic algorithm to automatically design neural network structures for classifying datasets. It allows users to experiment with evolving atypical network architectures rather than manually configuring layers and neurons. The tool borrows datasets from TensorFlow Playground and provides an interactive demo where users can observe how the algorithm produces efficient, unconventional network designs for solving classification problems.
written from the facts on this page · September 2026
From the sources
GitHub
This demo will attempt to use a genetic algorithm to produce efficient, but atypical neural network structures to classify datasets borrowed from TensorFlow Playground. Please try the demo here . A few weeks ago, Google released a Web Demo called TensorFlow Playground . If you haven’t played with it yet, I do encourage you to do so, as it is a really well designed web demo displaying the training progress of how a neural network handles a simple classification problem with a few dummy datasets. You get to customise many aspects of the network, such as the number of layers, neurons per layer and its activation function, initial input features, and so on. One of the things that interested me…from blog.otoro.net
Does a similar job
all alternatives →
Machine Learning Playground2017 · ml-playground.com · ▲169Breathtaking visuals for learning ML techniques.
Netmind Power2023 · netmind.ai · ▲272Hi HN, We just opened public access to Qwen3‑Coder‑480B‑A35B‑Instruct via a REST/SDK API. Why it might be interesting: - Fully open-source (Apache‑2.0): https://github.com/QwenLM/Qwen3-Coder - 480B params (35B active MoE), long context up to 1M tokens with YaRN - Matches Claude Sonnet/GPT‑4o on SWE-Bench Verified (81.6%) - Free tier: 100K tokens/month
AI Playground by Vercel Labs2023 · play.vercel.ai · ▲249Hey, Jared Palmer (creator of this playground) here. Really excited to ship this. I’ve been building this over the past few weeks to compare LLMs from different providers like OpenAI, Anthropic, Cohere, etc. At Vercel, I manage our Frameworks division (including Next.js, Svelte, and Turbo) and wanted to also dogfood some of the latest features in a slightly larger application. This playground takes a lot of inspiration from https://nat.dev and is built on Tailwind, ui.shadcn.com, and some upcoming Vercel products we’re announcing soon. We’re going to continue adding models to…
Boldly go where Gradient Descent has never gone before with DiscoGrad2024 · github.com · ▲232Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this might be interesting to you. We develped DiscoGrad, a tool for automatic differentiation through C++ programs involving input-dependent control flow (e.g., "if (f(x) < c) { ... }", differentiating wrt. x) and randomness. Our initial motivation was to enable the use of gradient descent with simulations, which often rely heavily on such discrete branching. The latter makes plain autodiff mostly useless, since it can only account for the…
Recurrent neural net plays 'neural slime volleyball' in JavaScript2015 · otoro.net · ▲147
Watch a neural net learn to play SnakeMay 2026 · ppo.gradexp.xyz · ▲205In browser PPO training demo, made possible by tinygrad: TinyJit -> WebGPU kernels. Requires WebGPU.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, May 2016
the whole month →
Gboard by Google▲1,207Google Search, GIFs, emojis & more—right from your keyboard
Life & fun · 2016 · apps.apple.com
