Simple MLP - NeuralNetwork Library For Microcontrollers

Nothing "Import ant", just a simple library for implementing Neural-Networks(NNs) easily and effectively on any Arduino board and other microcontrollers.

`Summary`

NN Functions	Input Type (x)	Output Type (Y)	Action
`*FeedForword(X)`	1D Float Array	1D Float Array	"Feeds" the NN with X-input values and returns Y-Output Values, If needed.
`*BackProp(x)`	1D Float Array	1D Float Array	Tells to the NN if the outputs-Y were right/the-expected-X-inputs and then, teaches it.

Examples: Backpropagation_Single_Xor_Gate.ino
Understanding the Basics of a Neural Network:
0 1 2 3 4 5 6 7 8 9 10 11 12 .
An Image that Explains some basic things.

`Features`

Current
- + Optimazed Algorithm For Less SRAM Usage.
- + Only Sigmoid Activation Function.
- + Use of PROGMEM.
- + Simplicity.
future
- - More Activation Functions.
- - Maybe Usage of External EEPROM.
- - Precise properties, for many different needs.

`Important`

ATtiny85 doesn't have FPU that makes Maths on it, "difficult" for the SRAM
If you want to Use "Serial" On An ATtiny85 Click Here (Be Careful SoftwareSerial Uses A lot of SRAM)
If you have Error with 'POINTER_REGS' Click Here
Backprop maths on An ATtiny85 doesn't work properly for some reasons, though Feed Forword maths Work! [...]
I am not yet a professional programmer [...]

`Tested On`

Arduino Uno
ATtiny85

`Examples`

*	Example Files (.ino)	Explenation
1	`Backpropagation_double_Xor`	NeuralNetwork Training of a 3-input-xor circuit and the print of the output(s) of it
2	`Backpropagation_Single_Xor_Gate`	NeuralNetwork Training of a xor gate and the print of the output(s) of it
3	`FeedForward_double_Xor`	print of the outputs of the pre-trained-NN
4	`FeedForward_double_Xor_PROGMEM`	print of the outputs of the pre-trained-NN using weights and biases from ROM

`Functions & Variables [...]`

NN = NeuralNetwork , LR = Learning Rate

NN Functions	Input Type (x),(z)	Output Type (Y)	Action
FeedForword(`inputs`)	1D Float Array	1D Float Array	"Feeds" the NN with X-input values and returns Y-Output Values, If needed.
FeedForword(`inputs`, `IS_PROGMEM`)	1D Float Array, Boolean	1D Float Array	"Feeds" the NN with X-input values and returns Y-Output Values, If needed. [Weights And Biases Saved in ROM]
BackProp(`*expected`)	1D Float Array	1D Float Array	Tells to the NN if the outputs-Y were right/the-expected-X-inputs and then, teaches it.
print(`IS__PROGMEM`)	Boolean	String	Serial.Prints the weights and biases of NN. If print(true) prints from ROM
NN.Layer[ i ].Sigmoid(`&x`)	Constant Float	Float	Returns Sigmoid Activation Function's 1/(1+e^(-x)) value

NN -Constructors -Variables -Layer's Variables	Type	Explenation
NeuralNetwork(`*_layer`, `&NumberOflayers`)	`const unsigned int`,	`Constructor`
NeuralNetwork(`*_layer`, `&NumberOflayers`, `&LRw`, `&LRb`)	`const unsigned int`, ,`const float`,	`Constructor`
NeuralNetwork(`_layer`, `default_Weights`, `*default_Bias`, `&NumberOflayers`)	`const unsigned int`,`float` , ,`const unsigned int`	`Constructor`
NeuralNetwork(`_layer`, `default_Weights`, `*default_Bias`, `&NumberOflayers`,`NO_OUTPUTS`)	`const unsigned int`,`float` , ,`const unsigned int`,`bool`	`Constructor` `NO_OUTPUTS` Clears Outputs from RAM
NN.`LearningRateOfWeights`	`float`	-
NN.`LearningRateOfBiases`	`float`	-
NN.`layers`[ i ]	`Layer*`	-
NN.Layer[ i ].`bias`	`float*`	-
NN.Layer[ i ].`outputs`[ j ]	`float*`	-
NN.Layer[ i ].`weights`[ j ][ l ]	`float**`	-
NN.Layer[ i ].`preLgamma`[ j ]	`float*`	-
NN.layers[ i ].`_numberOfInputs`	`unsigned int`	ReadOnly
NN.layers[ i ].`_numberOfOutputs`	`unsigned int`	ReadOnly

`Searches Across Internet`

| | Intresting |NN.| Neural Network(s) |A.| Arduino etc. |-| Mostly .NET & Other |*| Maybe Intresting?

NNs	PROGMEM	Define directive	Other & "Random"
`Playlist`	`Arduino`	`Tutorial`	A. Initialize Array Values
`Playlist`	`Manual`	`Arduino Define`	A. Inheritance,destructors?
`BackPropagation`	`Examples`	`Determining board`	A. Identifying Arduino type?
`Math Chain Rule`	+ Post	`define extern?`	A. Create compile error?
`Getting Started`	+ Pointers	.ino Determining Board	A. Measuring Memory Usage
+ BackProp Tutorial	+ Double Info	Understanding #if ?	A. External Memory
+ BackProp Tutorial	read-only?	Random Defined Site?	A. ATtiny85 Math Issues?
+ Complete NN chart !	flash to RAM?	Loading local libraries?	A. Attiny85 External Mem.?
+ MIT Deep RL	Info Near Far?		A. Splitting Array?
+ MIT Deep Learning	Example		A. Importing Loads Everything?
- `.NET Framework`	What is PGM_P?		`NN. Backprop. For Dummies YT`
- .NET ! 1,2,3,4,5,6	Passing Array?		`NN. Convolutional (Math- code)`
- C# Implementation, 2	Passing Array?		NN. In 4 minutes - Python
- .NET Deep NN	Reading?		NN. Quick Intro
* Predicting Languages	Easy data handling?		NN. -
* MIT Recurrent NNs	Reading Long?		NN. PyConSG 2016
- 2007 .NET Img Recognition	Multi-D Array?		NN. Simple 9 lines of Py-code
- C# Handwritten Recognition	Attiny85 mem?		NN. MIT Press book
`Youtube Chanel`	Prob Array use?		NN. A Beginner's Guide
+ Recurrent Explained	Double or float?		`NN. MIT courses?`
- .NET 1,2,3			`NN.Back Propagation`
- C# Handwritten Recognition			NN. MLP Maths?
+ Python NN From Scratch			NN. Math. Notations Into Code
* How Backpropagation!			NN. Maths Into Code
linear Regression			NN. (TAA),(BDI) Architecture
+ MLP			NN. fast.ai ?
+ MLP			NN. deeplearning.net
`🇬🇷` Νευρωνικά Δίκτυα			NN. BackProp Python
`🇬🇷` Γενετικός Αλγόριθμος			NN. C# Code
- MS NN Classification			NN. Implement BackProp Python
- VB ML Q-Learning			`NN. Java Tut Playlist` ?
* handwritten Recognition			NN. BackProp for Dummies
* Deep Learning in 6 weeks?			`NN. Wiki Backprop Math`
* Playlist			NN. Looking Inside
- `SciBasic`

`Notes`

Forgive me for my mistakes and maybe poor knowledge in C/C++, but it is also my first time making a "normal" library [...]
I am also sorry for my randomness in some parts of the Searches Across Internet Section.

Εικόνα που βλέπει το "εγώ", θυμίζει κουτί που δε βλέπεις, εικόνα που χάνεις• σκιά που 'τε φως και να βλέπεις, ακούει τα λόγια που λες: [...] ‮#i📁👁

I wish love and happiness to Everyone! <3

`Donation`

Bitcoin Address: 1Cfn2zb2XC5JAqTNjDYAxwKYVwtjqcf5Pm

kartben / NeuralNetworks