Artificial Neural Network (DL_ANN)

This function creates and uses a model consisting of layers of interconnected nodes (neurons) that process input data and produce output predictions.

An artificial neural network (ANN) is a type of machine learning model inspired by the structure and function of biological neurons in the human brain. It consists of layers of interconnected nodes (neurons) that process input data and produce output predictions. Each neuron takes in one or more inputs, applies a mathematical function to them, and passes the result to the next layer of neurons. By adjusting the weights and biases of the connections between neurons during training, the network can learn to make accurate predictions on new data. ANNs are used for a wide variety of tasks, including image and speech recognition, natural language processing, and predictive modeling.

Sample Request

Build a sequential ANN model for Binary Classification

{
    "project_id": 1,
    "parent_id": 7,
    "block_id": 8,
    "function_code": "DL_ANN_S_I",
    "args": {
        "layer_list": [
            {
                "type": "conv2d",
                "filters": 32,
                "kernel_size": [3, 3],
                "padding": "valid",
                "activation": "relu"
            },
            {
                "type": "maxpooling2d",
                "pool_size": [2, 2]
            },
            {
                "type": "upsampling2d",
                "size": [2, 2]
            },
            {
                "type": "flatten"
            },
            {
                "type": "dropout",
                "rate": 0.5,
            },
            {
                "type": "embedding",
                "input_dim": 1000,
                "output_dim": 64
            },
            {
                "type": "lstm",
                "units": 64,
                "return_sequences": false
            },
            {
                "type": "batchnormalization",
            {
                "type": "dense",
                "units": 1,
                "activation": "sigmoid"
            }
        ]
    }
}

Building a Sequential Artificial Neural Network

Sequential ANN Construction

POST https://autogon.ai/api/v1/engine/start

Request Body

Name	Type	Description
project_id*	int	The id of the current project
block_id*	int	The id of the current block
function_code*	string	The function code for current block
parent_id*	int	The id of the previous block
args*	object	Block arguments
layer_list*	list	List of layers for the Artificial Neural Network
type*	string	Type of layer to add
units*	int	Dimensionality of the output space of the layer
activation	string	Activation function applied to the layer's output. Default: "relu".
filters	int	Number of filters or output channels in the convolutional layer. Default: 32.
kernel_size	array	Size of the convolutional kernel. Default: [3, 3].
padding	string	Padding scheme for the layer. Default: "valid".
pool_size	array	Size of the pooling window. Default: [2, 2].
rate	float	Fraction of input units to drop during training (0-1). Default: 0.5.
input_dim	int	Size of the input vocabulary. Default: 1000.
output_dim	int	Dimensionality of the dense embedding. Default: 64.
return_sequences	bool	Whether to return the full sequence or only the last output. Default: false.
size	array	The upsampling factors for rows and columns. Default: [2, 2].

200 Statemanagement object

{
    "status": "true",
    "message": {
        "id": 8,
        "project": 1,
        "block_id": 8,
        "parent_id": 7,
        "dataset_url": "",
        "x_value_url": "",
        "y_value_url": "",
        "x_train_url": "",
        "y_train_url": "",
        "x_test_url": "",
        "y_test_url": "",
        "output": {}
    }
}

Sample Request

Compile and train the pre-built ANN model, using passed-in Hyper Parameters

{
    "project_id": 1,
    "parent_id": 8,
    "block_id": 9,
    "function_code": "DL_ANN_T",
    "args": {
        "model_name": "titanic_model",
        "add_dim": false,
        "hyp_params":{
            "optimizer": "adam",
            "loss": "binary_crossentropy",
            "metrics": ["accuracy"],
            "batch_size": 12,
            "epochs": 5,
            "autoencoder": false
        }
    }
}

Training an Artificial Neural Network

ANN Training

POST https://autogon.ai/api/v1

Request Body

Name	Type	Description
project_id*	int	The id of the current project
hyp_params*	object	hyper parameters for model compilation and training
parent_id*	int	The id of the previous block
block_id*	int	The id of the current block
function_code*		The function code for current block
args*	object	Block arguments
model_name*	String	The name the model would be saved with
optimizer	String	Optimization function to be used e.g: "adam"
loss*	String	Loss function to be used e.g: "binary_crossentropy"
metrics	list	Evaluation metrics used to judge the performance of the model
batch_size	String	Number of samples that are processed by the model during each training iteration
epochs*	String	Number of iterations through the dataset
add_dim	bool	Sets whether an extra dimension should be added to x train data
autoencoder	bool	Specifies whether to use x data as y data

200: OK Statemanagement Object

{
    "status": "true",
    "message": {
        "id": 9,
        "project": 1,
        "block_id": 9,
        "parent_id": 8,
        "dataset_url": "",
        "x_value_url": "",
        "y_value_url": "",
        "x_train_url": "",
        "y_train_url": "",
        "x_test_url": "",
        "y_test_url": "",
        "output": {}
    }
}

Sample Request

Evaluate the accuracy and losses of a trained artificial neural network.

{
    "project_id": 1,
    "parent_id": 8,
    "block_id": 9,
    "function_code": "DL_ANN_E",
    "args": {
        "hyp_params": {
            "batch_size": 32
        }
    }
}

Evaluating an Artificial Neural Network

ANN Evaluating

POST

Request Body

Name	Type	Description
project_id*	int	The id of the current project
parent_id*	int	The id of the previous block
block_id*	int	The id of the current block
function_code*	String	Function code for the current block
args*	object	Block arguments
hyp_params*	object	hyper parameters for model evaluation
batch_size	int	Number of samples that are processed by the model during evaluation

200: OK Statemanagement object

{
    "status": "true",
    "message": {
        "id": 9,
        "project": 1,
        "block_id": 9,
        "parent_id": 8,
        "dataset_url": "",
        "x_value_url": "",
        "y_value_url": "",
        "x_train_url": "",
        "y_train_url": "",
        "x_test_url": "",
        "y_test_url": "",
        "output": {}
    }
}

Sample Request

Make predictions with the trained ANN model.

{
    "project_id": 1,
    "parent_id": 8,
    "block_id": 9,
    "function_code": "DL_ANN_P",
    "args": {
        "test_data": ""
    }
}

Predicting with an Artificial Neural Network

ANN Predict

POST https://autogon.ai/api/v1/engine/start

Request Body

Name	Type	Description
test_data	String	Input data for prediction Defaults to x_test_url
project_id*	int	ID of the current project
block_id*	int	ID of the current block
parent_id*	int	ID of the previous block
function_code*	String	Function code for the current block
args*	object	Block arguments
add_dim	bool	Sets whether an extra dimension should be added to x data

200: OK Statemanagement object

{
    "status": "true",
    "message": {
        "id": 9,
        "project": 1,
        "block_id": 9,
        "parent_id": 8,
        "dataset_url": "",
        "x_value_url": "",
        "y_value_url": "",
        "x_train_url": "",
        "y_train_url": "",
        "x_test_url": "",
        "y_test_url": "",
        "output": {}
    }
}

Python

// Some code

Node

// Some code