playground
BezierInfo-2
Our great sponsors
playground | BezierInfo-2 | |
---|---|---|
16 | 20 | |
11,674 | 2,266 | |
1.1% | - | |
0.0 | 5.0 | |
3 months ago | about 2 months ago | |
TypeScript | HTML | |
Apache License 2.0 | GNU General Public License v3.0 or later |
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.
BezierInfo-2
- Flattening Bézier Curves and Arcs
-
Solution needed
For the bezier you need 4 control points via a click, then evaluate using lerps (or basis functions). Start here https://pomax.github.io/bezierinfo/
-
Hexagonal Grids
> How to pack geometric shapes inside other shapes https://erich-friedman.github.io/packing/
Packing / bin-packing is very serious stuff: savings made there directly translate to less waste / reduced costs (for example when cutting shapes into sheets of metal in big factories).
> * Amazing reference on bezier curves https://pomax.github.io/bezierinfo/
And some beautiful graphs in there, notably those under section 26 "Curvature of a curve". Screenshot'ed for my own collection of good looking stuff!
-
Visualization of Common Algorithms
https://pomax.github.io/bezierinfo/#explanation
A visual overview of commonly used creative coding related techniques and algorithms.
- A Primer on Bézier Curves
-
Text Rendering Hates You
I wrote an openGL font renderer once, it was a lot of fun. Bezier curves are such an elegant technique. The difference between what I wrote and what you'd use in a proper environment is pretty big, but I recommend it sometime.
Fonts are pretty much just third or fourth degree beziers, iirc (i may have my terminology wrong). Try it out sometime, I did mine using tessellation shaders.
Btw, you'll never find a better guide on beziers than here:
https://pomax.github.io/bezierinfo/
-
How to get the smoothness of a cubic Bezier curve in Apache Commons math3.
Alternatively you can use the equation of a cubic Bézier curve to do the computations yourself. This website offers great explanations and examples of the math behind Bézier curves: https://pomax.github.io/bezierinfo/
-
[Media] I'm making a new open source font editor with gtk-rs. I just managed to make non-linear curves with my Bézier path tool for the first time!
Btw, for Bezier math this is a great resource: https://pomax.github.io/bezierinfo/
- Transforming a parametric equation into explicit equation
- Linii bezier cu coliziune
What are some alternatives?
clip-interrogator - Image to prompt with BLIP and CLIP
BezierCurveTool2.0
dspy - DSPy: The framework for programming—not prompting—foundation models
CAM6 - Cellular Automata Machine (CAM6) Simulator
nvim-treesitter - Nvim Treesitter configurations and abstraction layer
bezmouse - Simulate human mouse movements with xdotool
pyllama - LLaMA: Open and Efficient Foundation Language Models
spiral_cube - How to convert between spiral and cube hexagonal coordinate systems
lake.nvim - A simplified ocean color scheme with treesitter support
SoftwareRenderer - Software rendering engine with PBR. Built from scratch on C++.
developer - the first library to let you embed a developer agent in your own app!
Skia - Skia is a complete 2D graphic library for drawing Text, Geometries, and Images.