playground
scratch-www
Our great sponsors
playground | scratch-www | |
---|---|---|
16 | 803 | |
11,674 | 1,559 | |
1.1% | 1.0% | |
0.0 | 9.9 | |
3 months ago | about 24 hours ago | |
TypeScript | JavaScript | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" License |
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.
playground
-
Why do tree-based models still outperform deep learning on tabular data? (2022)
Not the parent, but NNs typically work better when you can't linearize your data. For classification, that means a space in which hyperplanes separate classes, and for regression a space in which a linear approximation is good.
For example, take the circle dataset here: https://playground.tensorflow.org
That doesn't look immediately linearly separable, but since it is 2D we have the insight that parameterizing by radius would do the trick. Now try doing that in 1000 dimensions. Sometimes you can, sometimes you can't or do want to bother.
-
Introduction to TensorFlow for Deep Learning
For visualisation and some fun: http://playground.tensorflow.org/
- TensorFlow Playground – Tinker with a NN in the Browser
-
Visualization of Common Algorithms
https://seeing-theory.brown.edu/
https://www.3blue1brown.com/
https://playground.tensorflow.org/
-
Stanford A.I. Courses
There’s an interactive neural network you can train here, which can give some intuition on wider vs larger networks:
https://mlu-explain.github.io/neural-networks/
See also here:
http://playground.tensorflow.org/
-
Let's revolutionize the CPU together!
This site is worth playing around with to get a feel for neural networks, and somewhat about ML in general. There are lots of strategies for statistical learning, and neural nets are only one of them, but they essentially always boil down into figuring out how to build a “classifier”, to try to classify data points into whatever category they best belong in.
-
Curious about Inputs for neural network
I don’t know much experimenting you’ve done, but many repeated small scale experiments might give you a better intuition at least. I highly recommend this online tool for playing with different environmental variables, even if you’re comfortable coding up your own experiments: http://playground.tensorflow.org
-
Intel Announces Aurora genAI, Generative AI Model With 1 Trillion Parameters
Even if you can’t code, play around with this tool: https://playground.tensorflow.org — you can adjust the shape of the NN and watch how well it classifies the data. Model size obviously matters.
-
Where have all the hackers gone?
I don't think so. You can easily play around in the browser, using Javascript, or on https://processing.org/, https://playground.tensorflow.org/, https://scratch.mit.edu/, etc.
If anything the problem is that today's kids have too many options. And sure, some are commercial.
-
[Discussion] Questions about linear regression, polynomial features and multilayer NN.
Well there is no point of using a multilayer linear neural network, because a cascade of linear transformations can be reduced to a single linear transformation. So you can only approximate linear functions. However if you have prior knowledge about the non linearity of your data lets say you know that it is a linear combination of polynomials up to certain degree, you can expand your input space by explicitly making non linear transformation. For instance a 1D linear regression can be modeled by 2 input neurons and 1 output neuron where the activation of the output is the identity. The input neuron x0 will take a constant input namely 1 and the second input neuron x1 will takes your data x. The output neuron will be y=w_0 * 1+w_1 *x which is equal to y=w_0 +w_1 * x. Let us say that your data follows a polynomial form, the idea is to add input neurons and expand your input to for instance X=[1 x x2] in this case you have 3 input neurons where the third is an explict non linear form of the input so y=w_0 + w_1 x +w_2 x2. The general idea is to find a space where the problem becomes linear. In real life example these spaces are non trivial the power of neural network is that they can find by optimization such space without explicitly encoding these non linearities. Try playing around with https://playground.tensorflow.org/ you can get an intuition about your question.
scratch-www
- Scratch is the largest free coding community for kids
-
Screen-free coding for children: the xylophone maze
and https://codecombat.com, which has been around for a while now.
I think this paradigm (navigating a character using "move" function invocations) is good but kind of exhausts its usefulness after a while. I question whether my daughter learns coding this way or just is playing a turn based top down platformer. The most code like thing is when you use 'loops' to have characters repeat sequences of moves. I think when kids grok these things these apps become just types of glofiried education flavoured video games. There are a lot of things in kodable for instance that I feel are just basic web games with coding terms slapped on it.
https://scratch.mit.edu/ is more like 'programming' imo, even at the level of the objective -- having a blank canvas to create something. It seems a little advanced for my kids right now though.
-
Ask HN: Yo wants to build a game, I'm lost. What can I do?
+1 Scratch! My son started with it, then expanded into Roblox/Lua.
Children can download other people's games and experiment there. Scratch also has pre-made art, sounds, music.
https://scratch.mit.edu/
-
Ask HN: Platform for kids to learn how to code
Scratch.mit.edu is a highly-recommended place to start [1] https://scratch.mit.edu/
> Scratch is the world’s largest coding community for children and a coding language with a simple visual interface that allows young people to create digital stories, games, and animations. Scratch is designed, developed, and moderated by the Scratch Foundation, a nonprofit organization. [2]
1: https://scratch.mit.edu/
-
Eligiendo un computador para desarrollo
https://scratch.mit.edu/ (Scratch version 2)
-
i swear to god if i keep seeing projects abt these 4 franchises every single day i'm gonna break someone's kneecaps
Someone who uses scratch.mit.edu (like me)
-
How to learn coding without a degree
Now that I think of it, I did start game development on scratch before going right into java (because of minecraft).
- Copii si programarea
- Teen school project
-
Ask HN: Best tools for 4/5 year old to learn programming?
I'm looking for the best systems to help a 4/5 year old get the basics of programming. My daughter has shown interest in what I do, and loves puzzles and building things. Looking for something visual and fun that can start her down the path of logic and creating with computers.
I have a passing familiarity with Scratch [1], which I'm now looking into more, but am hoping others can share their knowledge and experience in this area.
[1] https://scratch.mit.edu/
What are some alternatives?
clip-interrogator - Image to prompt with BLIP and CLIP
Node RED - Low-code programming for event-driven applications
dspy - DSPy: The framework for programming—not prompting—foundation models
GDevelop - :video_game: Open-source, cross-platform game engine designed to be used by everyone.
nvim-treesitter - Nvim Treesitter configurations and abstraction layer
blockly - The web-based visual programming editor.
pyllama - LLaMA: Open and Efficient Foundation Language Models
Godot - Godot Engine – Multi-platform 2D and 3D game engine
lake.nvim - A simplified ocean color scheme with treesitter support
processing - Source code for the Processing Core and Development Environment (PDE)
developer - the first library to let you embed a developer agent in your own app!
stencyl-engine - Create Flash, HTML5, iOS, Android, and desktop games with no code with Stencyl. This is the source to Stencyl's Haxe-based engine.