DEEP LEARNING IN THE CLOUD

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

Sign Up

What is Deep Learning?

Deep Learning is the name given to neural network research after 2006. Neural networks are machine learning algorithms modeled after the branching neuronal structure of our brains. Machine learning is a discipline primarily focused on getting computers to program themselves. Deep learning turns out to be a good way to do this.

Deep learning has attractive characteristics for data scientists:
  • Scales to arbitrarily large datasets ("Big Data" is no longer a problem)
  • Breakthrough predictive accuracy on image, audio, text, and video datasets
  • Less feature engineering because neural networks learn their own features
Deep learning has many applications:
  • Medical imaging: Given a medical scan, what's wrong with me?
  • Video recognition: Given a video, describe what's happening and what's being said.
  • Image tagging: Given millions of images, tag them all in seconds.
  • Finance: Given information about a portfolio, recommend companies I might be interested in.
  • Text processing: Can negative internet comments be automatically filtered out?
  • Business analytics: Cluster CRM data to uncover new opportunities.

What does Ersatz do?

Deep learning, as it turns out, is hard. Ersatz is designed to make deep learning easier in practice. Deep learning is hard because:
  • Deep learning libraries like Theano, Torch, and Caffe are geared towards machine learning researchers, not businesses and mere mortals
  • These libraries provide limited visualization functionality
  • They provide limited data wrangling functionality
  • They provide no web-based API to make integration simple
  • They do not represent a complete pipeline for deep learning in practice
Ersatz helps with all of that
  • Ersatz is powered by open source (Theano and pylearn2 primarily)
  • We provide web-based data wrangling functionality
  • Model training dashboards make training ensembles of models super easy
  • Ersatz provides sophisticated visualization options
  • We offer a ready to use API to get your models into your software

Screenshots



Ready to give Ersatz a try?

No credit card required. Try it today.

FAQ

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, 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. With deep learning, "too much data" becomes a high quality problem.

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.

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.