Restricted Boltzmann Machine (DL_RBM)

This function creates a Restricted Boltzmann Machine used for dimensionality reduction

An RBM is a type of neural network used for unsupervised learning. It has two layers of neurons - visible and hidden - that are connected by weights. RBMs are unique because they have symmetric connections between the visible and hidden layers and no connections within the same layer. They use contrastive divergence to adjust the weights and learn complex probability distributions of the input data. RBMs are used in applications such as image and speech recognition, dimensionality reduction, and collaborative filtering. They can learn without labeled data and be used as building blocks for larger neural network architectures.

Sample Request

Build an RBM for data clustering

{
    "project_id": 1,
    "parent_id": 7,
    "block_id": 8,
    "function_code": "DL_RBM_I",
    "args": {
    "hyp_params":{
            "n_components": 5,
            "n_iter": 5
        }
    }
}

Building a Restricted Boltzmann Machine

RBM 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
n_components	int	Number of binary hidden units
n_iter	int	Number of iterations over the dataset
random_state	int	Pass an int for reproducible results across multiple function calls
learning_rate	float	The learning rate for weight updates

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 RBM model, using passed in Hyper Parameters

{
    "project_id": 1,
    "parent_id": 8,
    "block_id": 9,
    "function_code": "DL_RBM_T",
    "args": {
        "model_name": "titanic_model",
        "hyp_params":{
        }
    }
}

Training a Restricted Boltzmann Machine

RBM 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

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 RBM model.

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

Predicting with a Restricted Boltzmann Machine

RBM Predict

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

Request Body

Name	Type	Description
test_data*	String	Input data for prediction
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

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