Autogon Docs
  • Change Log
  • Get Started
  • Libraries
  • Slicing & Indexing
  • Autogon Engine (Studio)
    • Data Processing
      • Data Input (DP_1)
      • Automated Data Processing (DP_ADP)
      • Missing Data (DP_2)
      • Data Encoding (DP_3)
      • Data Split (DP_4)
      • Feature Scaling (DP_5)
      • Drop Columns (DP_6)
      • Time Stepper (DP_7)
      • Parse Datetime (DP_PDT)
      • Reorder Columns (DP_ROC)
      • Feature Sampling (DP_FSP)
      • Reshape Array (DP_RSH)
      • Column Astype (DP_ASP)
      • Show Duplicates (DP_SDC)
      • Drop Duplicates (DP_DRD)
      • Scalar to Ndarray (DP_STN)
      • Image to Ndarray (DP_ITN)
      • Dataset Info (DP_INF)
      • Dataset Correlations (DP_CRR)
      • Dataset Description (DP_DSC)
      • Dataset Datatypes (DP_DTY)
      • Dataset Uniques (DP_UNQ)
      • Dataset Stats Counts (DP_STC)
      • Principal Component Analysis (DP_PCA)
      • Text Vectorizer (DP_VEC)
      • Resampler (DP_RES)
    • Data Visualization
      • Scatter Plots (DP_SCP)
      • Ordinary Plots (DP_ORD)
      • Compare Scatter Plots (DP_CSP)
      • Pie Plots (DP_PIE)
      • Heatmap Plots (DP_HMP)
    • Machine Learning
      • Simple Linear Regression (ML_R_1)
      • Multiple Linear Regression (ML_R_2)
      • Polynomial Linear Regression (ML_R_3)
      • Support Vector Regression (ML_R_4)
      • Decision Tree Regression (ML_R_5)
      • Random Forest Regression (ML_R_6)
      • Logistic Regression (ML_CN_1)
      • K-Nearest Neighbors - KNN (ML_CN_2)
      • Support Vector Machine (ML_CN_3)
      • Kernel SVM (ML_CN_4)
      • Naive Bayes (ML_CN_5)
      • Decision Tree Classification (ML_CN_6)
      • Random Forest Classification (ML_CN_7)
      • Hierarchical Clustering (ML_CG_1)
      • K-Means Clustering (ML_CG_2)
      • XGBoost (MS_XGBOOST)
      • Grid Search (ML_GRID)
      • Shap Explain (ML_SHAP)
      • Isolation Forest (ML_ISF)
      • (ML_DBS)
    • Automated Machine Learning
      • AutoRegression (AUTO_R_1)
      • AutoClassification (AUTO_CN_1)
      • AutoRegression II (AUTO_R_2)
    • Deep Learning
      • Artificial Neural Network (DL_ANN)
      • Self Organizing Maps (DL_SOM)
      • Restricted Boltzmann Machine (DL_RBM)
    • Automated Deep Learning
      • Auto Image Classification (A_DL_IMC)
      • Auto Image Regression (A_DL_IMR)
      • Auto Text Classification (A_DL_TXC)
      • Auto Text Regression (A_DL_TXR)
      • Auto Structured Data Classification (A_DL_SDC)
      • Auto Structured Data Regression (A_DL_SDR)
      • General AutoDL Blocks (A_DL_ALL)
  • LabelCraft
    • Images, Annotations and Augmentation
    • Import and Export
    • Model Training and Prediction
  • Production APIs
    • Production Pipelines
  • Autogon Qore
    • Vision AI
    • Natural Language AI
      • Text Classification (Deprecated)
      • Text Summary (Deprecated)
      • Ask Your Data
      • Generate Synthetic Data
      • Speech To Text
      • Text To Speech
      • Sentiment Analyzer (Deprecated)
      • Conversation with Chatbot Agent
      • Conversational Interaction with GPT-4
      • Essay Marker
      • Resume Ranker
      • Translator
    • Voice Cloning
      • Create a Voice
      • Get Voices
      • Text-To-Speech
  • Other APIs
    • Project
      • List all projects
      • Create a New Project
      • Get Project Details
      • Delete a Project
    • Dataset
      • List all datasets
      • Create a Dataset
      • Get a Dataset
      • Updating a dataset
      • Delete a Dataset
      • Dataset Connection
      • Visualize Dataset
Powered by GitBook
On this page
  • Sample Request
  • Building a Restricted Boltzmann Machine
  • RBM Construction
  • Sample Request
  • Training a Restricted Boltzmann Machine
  • RBM Training
  • Sample Request
  • Predicting with a Restricted Boltzmann Machine
  • RBM Predict

Was this helpful?

  1. Autogon Engine (Studio)
  2. Deep Learning

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

{
    "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

{
    "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

{
    "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": {}
    }
}

// Some code
// Some code
PreviousSelf Organizing Maps (DL_SOM)NextAutomated Deep Learning

Last updated 1 year ago

Was this helpful?