Neural Networks in R

Topic Overview

Hello, and welcome to the journey of understanding and implementing neural networks using R! Neural networks are a cornerstone of machine learning and AI, enabling innovative solutions across many domains. In this lesson, you will learn how to create and define a simple neural network using the keras3 package in R. You will also gain an understanding of the components of a neural network, including layers, weights, biases, and activation functions.

Introduction to Neural Networks

Neural networks are computational systems inspired by the human brain. They consist of neurons (the most basic unit), which are assembled in layers to make the network. Each neuron in one layer is connected to neurons in the next layer through synaptic weights. Moreover, each neuron has a bias that allows shifting the neuron's activation threshold. An activation function regulates the output of a neuron given a set of inputs and the weights associated with them. One popular activation function is the ReLU (Rectified Linear Unit) activation function. Neurons and layers play essential roles in neural networks, and understanding them is key to building effective models. Visualizing a simple neural network with an input layer, a hidden layer, and an output layer: In the above image, the input layer receives the data, the hidden layer processes it, and the output layer provides the final result. The hidden layer is where the magic happens, as it transforms the input data into a form that can be used to make predictions. In the graphical representation, each circle represents a neuron, and the lines connecting them represent the weights. The weights are adjusted during the training process to minimize the error in the model's predictions. Such a network can be used for various real-world applications, such as image recognition, natural language processing, and more — for example, predicting the price of a house based on its features or classifying an image as a cat or a dog.

Implementing Neural Networks using R and keras3

We will build a neural network using the powerful keras3 package in R. Let's start by setting the backend and loading the required library: R # Tell Keras to use TensorFlow as backend Sys.setenv(KERAS_BACKEND = "tensorflow") library(keras3) Now that we have our library, we will accomplish the following steps: Initialize a Sequential Neural Network. Add an input and hidden layer. Add an output layer. Compile the model. Train and evaluate the model.

Join the 1M+ learners on CodeSignal

Be a part of our community of 1M+ users who develop and demonstrate their skills on CodeSignal

model <- keras_model_sequential()

model <- keras_model_sequential()

model <- keras_model_sequential() |>
  layer_dense(units = 64, activation = "relu", input_shape = 20)

model <- keras_model_sequential() |>
  layer_dense(units = 64, activation = "relu", input_shape = 20)

model <- model |>
  layer_dense(units = 10, activation = "softmax")

model <- model |>
  layer_dense(units = 10, activation = "softmax")

model |> compile(
  loss = "categorical_crossentropy",
  optimizer = "adam",
  metrics = "accuracy"
)

model |> compile(
  loss = "categorical_crossentropy",
  optimizer = "adam",
  metrics = "accuracy"
)

text

Model: "sequential"
________________________________________________________________________________
 Layer (type)                Output Shape              Param #   
================================================================================
 dense (Dense)               (None, 64)                1344     
 dense_1 (Dense)             (None, 10)                650      
================================================================================
Total params: 1994 (7.79 KB)
Trainable params: 1994 (7.79 KB)
Non-trainable params: 0 (0.00 B)
________________________________________________________________________________

Model: "sequential"
________________________________________________________________________________
 Layer (type)                Output Shape              Param #   
================================================================================
 dense (Dense)               (None, 64)                1344     
 dense_1 (Dense)             (None, 10)                650      
================================================================================
Total params: 1994 (7.79 KB)
Trainable params: 1994 (7.79 KB)
Non-trainable params: 0 (0.00 B)
________________________________________________________________________________

# Dummy training data
x_train <- matrix(runif(1000 * 20), nrow = 1000, ncol = 20)
y_train <- keras3::to_categorical(sample(0:9, 1000, replace = TRUE), 10)

# Train the model
model |> fit(x_train, y_train, epochs = 5, batch_size = 32, validation_split = 0.2)

# Dummy training data
x_train <- matrix(runif(1000 * 20), nrow = 1000, ncol = 20)
y_train <- keras3::to_categorical(sample(0:9, 1000, replace = TRUE), 10)

# Train the model
model |> fit(x_train, y_train, epochs = 5, batch_size = 32, validation_split = 0.2)

model <- keras_model_sequential()

model <- keras_model_sequential() |>
  layer_dense(units = 64, activation = "relu", input_shape = 20)

model <- model |>
  layer_dense(units = 10, activation = "softmax")

model |> compile(
  loss = "categorical_crossentropy",
  optimizer = "adam",
  metrics = "accuracy"
)

text

Model: "sequential"
________________________________________________________________________________
 Layer (type)                Output Shape              Param #   
================================================================================
 dense (Dense)               (None, 64)                1344     
 dense_1 (Dense)             (None, 10)                650      
================================================================================
Total params: 1994 (7.79 KB)
Trainable params: 1994 (7.79 KB)
Non-trainable params: 0 (0.00 B)
________________________________________________________________________________

# Dummy training data
x_train <- matrix(runif(1000 * 20), nrow = 1000, ncol = 20)
y_train <- keras3::to_categorical(sample(0:9, 1000, replace = TRUE), 10)

# Train the model
model |> fit(x_train, y_train, epochs = 5, batch_size = 32, validation_split = 0.2)

Topic Overview

Introduction to Neural Networks

Implementing Neural Networks using R and keras3

Join the 1M+ learners on CodeSignal

Initializing a Sequential Neural Network

Adding Input and Hidden Layers

Adding the Output Layer

Compiling the Model

Printing Model Summary and Output Example

Training the Model (Example with Dummy Data)

Evaluation and Summary