8/12/22, 7:41 PM A Neural Network Playground

Tinker With a Neural Network in Your Browser.

(https://git

Don’t Worry, You Can’t Break It. We Promise.

Epoch Learning rate Activation Regularization Regularization rate Problem type

repl
sk 001,364 0.03 arrow_drop_down ReLU arrow_drop_down None arrow_drop_down 0 arrow_drop_down Classification arrow_drop_down

DATA FEATURES

adre 2 HIDDEN LAYERS OUTPUT

Which dataset Which Test loss
0.047
do you want to properties do Training loss
0.031
use? you want to adre adre
feed in? 5 neurons 4 neurons 6

5
X1
4

3
X2 2

1
Ratio of training
0
to test X12
-1
data:  70%
-2
X22 -3

Noise:  5 -4

The outputs are -5

X1X2
mixed with varying -6
weights,
-6 shown
-5 -4 -3 -2 -1 0 1 2 3 4 5 6
Batch size:  20
by the thickness of
sin(X1) This is the output the lines.
from one neuron.
Hover to see it Colors shows
REGENERATE larger. data, neuron and
sin(X2) -1 0 1
weight values.

Show test data Discretize output

ke

Um, What Is a Neural Network?

It’s a technique for building a computer program that learns from data. It
is based very loosely on how we think the human brain works. First, a
collection of software “neurons” are created and connected together,
allowing them to send messages to each other. Next, the network is
asked to solve a problem, which it attempts to do over and over, each
time strengthening the connections that lead to success and diminishing
those that lead to failure. For a more detailed introduction to neural
networks, Michael Nielsen’s Neural Networks and Deep Learning
(http://neuralnetworksanddeeplearning.com/index.html) is a good place
to start. For a more technical overview, try Deep Learning
(http://www.deeplearningbook.org/) by Ian Goodfellow, Yoshua Bengio,
and Aaron Courville.

This Is Cool, Can I Repurpose It?

Please do! We’ve open sourced it on GitHub

(https://github.com/tensorflow/playground) with the hope that it can make
neural networks a little more accessible and easier to learn. You’re free
to use it in any way that follows our Apache License

https://playground.tensorflow.org/#activation=relu&batchSize=20&dataset=spiral&regDataset=reg-plane&learningRate=0.03&regularizationRate=… 1/3