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... - Source: Hacker News / about 2 months ago
For visualisation and some fun: http://playground.tensorflow.org/. - Source: dev.to / 4 months ago
Https://seeing-theory.brown.edu/ https://www.3blue1brown.com/ https://playground.tensorflow.org/. - Source: Hacker News / 8 months ago
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/. - Source: Hacker News / 10 months ago
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. Source: 10 months ago
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. Source: 11 months ago
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. Source: 11 months ago
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. - Source: Hacker News / 12 months ago
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... Source: 12 months ago
We do understand how it works. Basically we feed lots of training data into a very big matrix of numbers and then optimize the numbers using well known calculus. It's easy to prove that this approach works for learning simple Mathematical problems. See for example https://playground.tensorflow.org. Source: almost 1 year ago
You can actually play with training a very simple model in your web browser here to get an idea of how that works. The important part though is that training is kind of a trial and error adjustment process. Source: about 1 year ago
This is pretty cool: https://playground.tensorflow.org/. Source: about 1 year ago
If you want to play with a (very simple) neural network yourself, you can go to https://playground.tensorflow.org/ ; the source code to this application is at https://github.com/tensorflow/playground. Source: about 1 year ago
Https://playground.tensorflow.org/ can be a good place to start to get some visual representation of it. Source: over 1 year ago
To really see the weight learning in realtime, I guess you are looking for something like playground but applicable to your owm models. Source: almost 2 years ago
Hm, during one of my machine learning courses we learned about this website: Http://playground.tensorflow.org It’s not exactly a fully platform, but it does help to learn about the effects of different parameters. Source: about 2 years ago
A good introduction to neural networks can be found here: https://playground.tensorflow.org A parameter is a "weight" in this case (the lines drawn from neuron to neuron). The neurons are effectively runtime values or "activations." Parameters (weights) are updated during training and then set as constant during "inference" (also called "prediction"). There's unfortunately a ton of jargon and different groups... - Source: Hacker News / about 2 years ago
Hello HN! I want to create a small animation that looks like the graph on https://playground.tensorflow.org/ (hit play to see the animation). I have a few images that I want to connect with those "animated paths". - Source: Hacker News / about 2 years ago
I thought I knew neural nets until I tried to fit the spiral on here https://playground.tensorflow.org. Source: about 2 years ago
Oh, that's really standard. "self-learning". Any of your typical neural networks do this by default. You can go play with one. No part of complexity or self-awareness prevent computers from driving their own output. Even polymorphic computer viruses do that and they're really tiny. Source: about 2 years ago
Not sure I'd have the time to work on this, but gonna drop this old idea here anyways. A long time ago I had the idea for a Swords and Sandals type game (a gladiator game) where each opponent was actually a simulated neural network and you could peak under the hood much like this.[0] Each gladiator would be simulated against each other and would actually be learning as they played against each other. Difficulty... - Source: Hacker News / about 2 years ago
Do you know an article comparing Deep playground to other products?
Suggest a link to a post with product alternatives.
This is an informative page about Deep playground. You can review and discuss the product here. The primary details have not been verified within the last quarter, and they might be outdated. If you think we are missing something, please use the means on this page to comment or suggest changes. All reviews and comments are highly encouranged and appreciated as they help everyone in the community to make an informed choice. Please always be kind and objective when evaluating a product and sharing your opinion.