$(document).ready(function(){ setInterval(fill_network, 500); $('#nn-container').hide(); }


Ersatz is a platform for software engineers looking to get more done with machine learning. It offers data wrangling, deep learning, and an API. Powered by excellent open source libraries like theano, pylearn2, and others.

Sign Up
Workshop: Video Recognition with Deep Learning
July 1 in San Francisco More information here
Wrangle data
Train models
Get results with our deep learning API
Live melanoma detection with our API from Simagis
Neural networks breaking CAPTCHA with our API

Ersatz Use-Cases


What ERSATZ does
Data Wrangling
The job of the data scientist must always start with "data wrangling". This comes after ETL--when you retrieve the pertinent data out of your databases, flat files, or cluster storage.

The data scientist must then perform a variety of transformations to normalize the data, split it into cross validation subsets, balance the class distributions, and more. These steps are typically time consuming and uninteresting.

The job of Ersatz starts at this stage--we provide tools to take your data from a preferred format--CSV for instance--and transform it into a dataset suitable for machine learning. Easily.
Deep Learning
Once your data has been wrangled, it's time to train some predictive models. Ersatz specializes in Deep Learning, a technique based on neural networks.

The flashing boxes above represent a neural network. Essentially, you provide some input data and a target label. Based on how the boxes are configured, a prediction will come out.

If you are familiar with linear algebra, you can think of it as a (rather complex) geometric transformation on some arbitrary vector. In plainer english, the neural network will take the input, apply its model, and arrive at an answer (right or wrong).

The neural network then compares its generated answer to the true answer (which you provide). If it was wrong, it adjusts its "mental model" just so. If it was right, it reconfigures itself differently. It does this over and over.
Once you are satisfied with the accuracy of your neural network, you can then use our API to add their functionality into your own software. In fact, you can use our API to upload new data and train new neural networks.

Actually integrating machine learning models is an often underestimated task. Having an API already built like the one we provide with Ersatz is very handy.

Ersatz Screenshots


Can Ersatz only be used in the cloud?

No, we also provide a deep learning appliance that can be installed in customer data centers. Inquire at info@ersatzlabs.com for more information.

What model architectures are currently supported?

Deep neural networks with convolutional, ReLu, maxout, or sigmoid units. Recurrent Neural Networks. T-SNE (a clustering algorithm)

What data formats are currently supported?

CSV data, time series data, and image data. Generally available video and text coming soon.

What fancy deep learning features do you provide?

Model ensembling, dropout averaging, Nesterov momentum, parameter annealing, bayesian hyperparameter optimization, and probably some others that improve accuracy and save on implementation time.

How do I set hyperparameters?

We provide functionality that uses machine learning to set the hyperparameters for you, based on models that have trained well on similar data in the past. We still let you set model parameters if you want, but we can also pick them for you.

How much data can I use?

Theoretically, it's unlimited because data is read in batches instead of all at once. In practice, you're limited by model capacity (IE number of neurons). Deep learning scales naturally to very large amounts of data, and this is one of the attractive aspects of the technique. If you're worried you have too much data, you should be using deep learning.

Who is the target user? Data scientists or marketing managers?

Our stereotypical user is an engineer with basic knowledge of machine learning. If you've watched the first few videos from Andrew Ng's Coursera class and know what an API is, you know enough to use Ersatz to get work done.

Do you use GPUs?

Yes, we use GPUs (Graphics Processing Units) to speed up the training time of our models by up to 30x.

Ready to give Ersatz a try?

No credit card required. Try it today.

Ersatz is a product of Ersatz Labs

Ersatz Labs is a team of web developers and machine learning researchers dedicated to providing the best machine learning tools on the market. While data science may be hard, we think we can make it easier.
Ersatz Labs, Inc.

80 Eureka Square, #212
Pacifica, CA 94044

contact: info@ersatzlabs.com

© 2014 Ersatz Labs, Inc.
All Rights Reserved.