Functions — github.com/Sentdex/NNfSiX

CodeHub MCPcopy Create free account

hub / github.com/Sentdex/NNfSiX / functions

Functions235 in github.com/Sentdex/NNfSiX

⨍ Functions 235◇ Types & classes 56

↓ 1 callersFunctionrand_range

Generate a random floating point number from min to max

C/p005-ReLU-Activation.c:79

↓ 1 callersFunctionrand_range

Generate a random floating point number from min to max

C/p006-Softmax-Activation.c:80

↓ 1 callersFunctionrand_range

generate a random floating point number from min to max

C/p004-Batches-Layers.c:66

↓ 1 callersMethodrandn

Implementation of randn function from numpy, uses the built in gaussian distribution from the java random class. @param rows How many rows the array

Java/P005ReLUActivationAndSpiralDataset.java:89

↓ 1 callersFunctionrandom

C++/p004-Layers-and-Object.cpp:16

↓ 1 callersFunctionsoftmax

(input: Array2<f64>)

Rust/p006-Softmax-Activation.rs:48

↓ 1 callersFunctionspiral_data

(points, classes)

Javascript/p005-ReLU-Activation.js:10

↓ 1 callersFunctionspiral_data

(points: usize, classes: usize)

Rust/p005-ReLU-Activation.rs:45

↓ 1 callersFunctionspiral_data

(points: usize, classes: usize)

Rust/p006-Softmax-Activation.rs:67

↓ 1 callersFunctionspiral_data

C++/p005-ReLU-Activation.cpp:123

↓ 1 callersFunctionspiral_data

@brief Generate a randome range in a uniform distribution. * @Note Credit to shreeviknesh (#106) saved alot of time. * * @param[in] points Num

C/p006-Softmax-Activation.c:195

↓ 1 callersMethodspiral_data

C#/p005-ReLU-Activation.cs:53

↓ 1 callersFunctionuniform_distribution

@brief Generate a randome range in a uniform distribution. * @Note Code was lifted from here https://stackoverflow.com/questions/11641629/generating-

C/p005-ReLU-Activation.c:179

↓ 1 callersFunctionuniform_distribution

@brief Generate a randome range in a uniform distribution. * @Note Code was lifted from here https://stackoverflow.com/questions/11641629/generating-

C/p006-Softmax-Activation.c:180

↓ 1 callersFunctionvector_flip_sign

C++/p006-Softmax-Activation.cpp:246

↓ 1 callersFunctionvector_mean

C++/p006-Softmax-Activation.cpp:238

MethodActivationReLU

C+nnfs c++ part 6.cpp:642

MethodActivationReLU

C++/p006-Softmax-Activation.cpp:734

MethodActivationSoftmax

C+nnfs c++ part 6.cpp:653

MethodActivationSoftmax

C++/p006-Softmax-Activation.cpp:745

MethodDisplayOutput

Method to Display Jagged Array as Matrix in Console

C#/p004-Layers-and-Objects.cs:76

Forward function

C#/p005-ReLU-Activation.cs:119

MethodLayerDense

C+nnfs c++ part 6.cpp:593

MethodLayerDense

C++/p006-Softmax-Activation.cpp:686

MethodLayer_Dense

C#/p005-ReLU-Activation.cs:86

MethodLayer_Dense

(int n_inputs, int n_neurons)

C#/p004-Layers-and-Objects.cs:15

MethodLayer_Dense

Constructor for new densely connected layer. @param n_inputs Number of inputs coming into layer. @param n_neurons Number of neurons in layer.

Java/P004LayersAndObjects.java:43

MethodLayer_Dense

Constructor for new densely connected layer. @param n_inputs Number of inputs coming into layer. @param n_neurons Number of neurons in layer.

Java/P005ReLUActivationAndSpiralDataset.java:68

(string[] args)

C#/p001-Basic-Neuron-3-inputs.cs:10

(string[] args)

C#/p005-ReLU-Activation.cs:20

(string[] args)

C#/p002-Basic-Neuron-Layer.cs:10

(string[] args)

C#/p003-Dot-Product.cs:11

(string[] args)

C#/p004-Layers-and-Objects.cs:52

FunctionNewSpiralData

NewSpiralData generates spiral data. see: https://cs231n.github.io/neural-networks-case-study/

Go/p005-ReLU-Activation.go:125

C+nnfs c++ part 6.cpp:124

To make generate the same set of random numbers (for debugging) comment out: std::mt19937 randomEngine(randomSeed()); uncomment: std::mt19937 randomEn

C+nnfs c++ part 6.cpp:522

C++/p006-Softmax-Activation.cpp:139

C+nnfs c++ part 6.cpp:538

C++/p006-Softmax-Activation.cpp:631

C+nnfs c++ part 6.cpp:563

C++/p006-Softmax-Activation.cpp:656

(self, n_inputs, n_neurons)

Python/p008-Categorical-Cross-Entropy-Loss-applied.py:14

(self, n_inputs, n_neurons)

Python/p005-ReLU-Activation.py:11

(self, n_inputs, n_neurons)

Python/p004-Layers-and-Object.py:15

(self, n_inputs, n_neurons)

Python/p006-Softmax-Activation.py:10

Functionactiavtion1

@brief Callback to apply a activation function to the output of a node. * * @param[in] output Pointer to the dot product output. */

C/p005-ReLU-Activation.c:167

Functionactiavtion1

@brief Callback to apply a activation function to the output of a node. * * @param[in] output Pointer to the dot product output. */

C/p006-Softmax-Activation.c:168

Functionactivation_sigmoid

sigmoid activation function

C/p005-ReLU-Activation.c:149

Functionactivation_sigmoid

sigmoid activation function

C/p006-Softmax-Activation.c:150

Methodconstructor

(n_inputs, n_neurons)

Javascript/p004-Layers-and-Object.js:14

Methodconstructor

(n_inputs, n_neurons)

Javascript/p005-ReLU-Activation.js:46

Methodconstructor

Javascript/p005-ReLU-Activation.js:60

Methoddense_layer

C++/p004-Layers-and-Object.cpp:67

Methoddense_layer

C++/p005-ReLU-Activation.cpp:103

fill matrix with num

C+nnfs c++ part 6.cpp:82

C++/p006-Softmax-Activation.cpp:92

Javascript/p005-ReLU-Activation.js:62

Python/p008-Categorical-Cross-Entropy-Loss-applied.py:22

Python/p008-Categorical-Cross-Entropy-Loss-applied.py:26

(self, y_pred, y_true)

Python/p008-Categorical-Cross-Entropy-Loss-applied.py:38

Python/p005-ReLU-Activation.py:19

Python/p006-Softmax-Activation.py:18

Python/p006-Softmax-Activation.py:22

Methodinitialize

( n_inputs, n_neurons)

Ruby/p004_Layers_And_Object.rb:17

C+nnfs c++ part 6.cpp:675

Rust/p005-ReLU-Activation.rs:6

Rust/p006-Softmax-Activation.rs:7

Rust/p004-Layers-and-Object.rs:9

Rust/p001-Basic-Neuron-3-inputs.rs:6

Rust/p002-Basic-Neuron-Layer.rs:4

Rust/p003-Dot-Product.rs:6

C++/p001-Basic-Neuron-3-inputs.cpp:9

C++/p004-Layers-and-Object.cpp:86

C++/p002-Basic-Neuron-Layer.cpp:9

C++/p003-Dot-Product.cpp:28

C++/p006-Softmax-Activation.cpp:767

C++/p005-ReLU-Activation.cpp:138

Go/p003-Dot-Product.go:8

Go/p002-Basic-Neuron-Layer.go:9

Go/p004-Layers-and-Object.go:43

Go/P001-Basic-Neuron-3-inputs.go:9

Go/p005-ReLU-Activation.go:73

Kotlin/P003DotProduct.kt:7

* Creates a simple layer of neurons, with 4 inputs. * Associated YT NNFS tutorial: https://www.youtube.com/watch?v=lGLto9Xd7bU */

Kotlin/P002BasicNeuronLayer.kt:5

* Creates a basic neuron with 3 inputs. * Associated YT NNFS tutorial: https://www.youtube.com/watch?v=Wo5dMEP_BbI */

Kotlin/P001BasicNeuron3Inputs.kt:5

C/p005-ReLU-Activation.c:250

C/p001-Basic-Neuron-3-inputs.c:8

C/p003-Dot-Product.c:49

C/p006-Softmax-Activation.c:297

C/p002-Basic-Neuron-Layer.c:8

C/p004-Batches-Layers.c:135

(String[] args)

Java/P002BasicNeuronLayer.java:10

(String[] args)

Java/P001BasicNeuron3Inputs.java:8

Main method, establishes data to be used, creates two layers and runs data through both layers to get output.

Java/P004LayersAndObjects.java:14

(String[] args)

Java/P003DotProduct.java:10

Main method, establishes data to be used, creates two layers and runs data through both layers to get output.

Java/P005ReLUActivationAndSpiralDataset.java:20

FunctionmatrixCapMax

caps max value in matrix at value

C+nnfs c++ part 6.cpp:298

FunctionmatrixGetMax

returns biggest value from whole of the matrix

C+nnfs c++ part 6.cpp:351

FunctionmatrixMinus

minus value from all the elements

C+nnfs c++ part 6.cpp:379

Functionmatrix_cap_max

caps max value in matrix at value

C++/p006-Softmax-Activation.cpp:327

← previous next →101–200 of 235, ranked by callers