Data Science Deployments with Docker

Posted by & filed under Data Science, Developers, Machine Learning Tutorials, Tutorials.

Deploying machine learning models has always been a struggle. Most of the software industry has adopted the use of container engines like Docker for deploying code to production, but since accessing hardware resources like GPUs from Docker was difficult and required hacky, driver specific workarounds, the machine learning community has shied away from this option.… Read more

The Simple + Practical Path to Machine Learning Capability: A Common Benchmark Task

Posted by & filed under Machine Learning, Machine Learning Tutorials, Tutorials.

Here we introduce optical character recognition as a common benchmark task in modern machine learning, and show how to implement a simple model. Being able to experiment with machine learning models is the first step towards capability! Scientific learning process –> machine learning process In the previous post, we introduced machine learning as a principled… Read more

The Simple + Practical Path to Machine Learning Capability: Motivating Background, Fundamental Concepts & Workflow

Posted by & filed under Developers, Machine Learning Tutorials.

Hello, friendly human! Welcome to the first in a series of articles about using machine learning to solve problems. We start with fundamental concepts, and later explain how to implement those concepts using Python + TensorFlow code. Then we’ll show how to combine and extend these fundamental concepts to solve more interesting problems. An unproductive… Read more

TensorFlow Data Input (Part 1): Placeholders, Protobufs & Queues

Posted by & filed under Machine Learning, Machine Learning Tutorials.

TensorFlow is a great new deep learning framework provided by the team at Google Brain. It supports the symbolic construction of functions (similar to Theano) to perform some computation, generally a neural network based model. Unlike Theano, TensorFlow supports a number of ways to feed data into your machine learning model. The processes of getting… Read more

Deep Advances in Generative Modeling

Posted by & filed under Machine Learning, Machine Learning Tutorials.

Earlier this month, Alec Radford — indico’s Head of Research — led a talk at Boston ML Forum. He presented an overview of recent work in generative modeling, including research that he, Luke Metz, and Soumith Chintala (FAIR) released in November 2015: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. Video and slides below.… Read more