Sign in
Sign in
or
Create a new account
Categories
Your Saved List Partners Sell in AWS Marketplace Amazon Web Services Home Help
Amazon SageMaker ×

Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.

DeepElement AutoML-Matrix Algorithm
Free Trial

By: Deep Element Latest Version: 0.1

Automatically build classification models for structured data

Product Overview

AutoML-Matrix is a proprietary self-learning Neural Network algorithm which can automatically build state-of-the-art classification models for data presented in a matrix (or tabular) form. Given a dataset, this algorithm determines the architecture of the Neural Net and then computes its parameters automatically, without the user having to provide the value of any hyperparameter (#layers, #neurons_per_layer, #learning_rate, e.t.c). This software automates the training pipeline by performing data pre-processing, feature engineering, model selection and hyperparameter optimization.

Key Data

Version
By Deep Element
Categories
Type Algorithm
Fulfillment Methods Amazon SageMaker

Usage Information

Fulfillment Methods

Amazon SageMaker

Can be used for classification problems

How to prepare input data

  • Data must be in a CSV file format (comma separated) with no header row
  • First column represents the class label and it should contain only integer values
  • Feature values can be only numeric (integer or floating point values)
  • There is no need to split the dataset into train/validation/test sets, the algorithm automatically does that internally (approx 90% for train & validation, ~10% for test)

Channel Specification train: contains training data (train, validation and test) Input modes: File Content types: csv Compression types: None

Hyperparameters None

Maximum Training Time Runtime of the training algorithm depends on various factors including number of data samples, number of features, the complexity of the problem itself. A rough approximation of Maximum Runtime based only on number of data samples is:

If #Samples < 100,000, then (2, 4) hrs If #Samples < 500,000, then (3, 6) hrs If #Samples < 1,000,000, then (6, 10) hrs If #Samples < 10,000,000, then (10, 20) hrs

Additional Resources

End User License Agreement

By subscribing to this product you agree to terms and conditions outlined in the product End User License Agreement (EULA)

Support Information

DeepElement AutoML-Matrix Algorithm

Support is available from Deep Element. Search for questions in FAQ and write to us at contactus@deepelement.ai

https://www.deepelement.ai/Projects/AutoML-Matrix

AWS Infrastructure

AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services. Learn more

Refund Policy

Deep Element will not refund payments made by you as the Service Fees for any reason whatsoever.

Customer Reviews