Jeremy Jordan

Machine learning engineer. Broadly curious.

Data Science

Training extremely large neural networks across thousands of GPUs.

In this blog post, we'll discuss techniques such as data and model parallelism which allow us to distribute the model training process across a large cluster of machines.

Data Science

Understanding the Transformer architecture for neural networks

The attention mechanism allows us to merge a variable-length sequence of vectors into a fixed-size context vector. What if we could use this mechanism to entirely replace recurrence for sequential modeling? This blog post covers the Transformer architecture which explores such an approach.

Data Science

Understanding the attention mechanism in sequence models

In this blog post, we'll discuss a key innovation in sequence-to-sequence model architectures: the attention mechanism. This architecture innovation dramatically improved model performance for sequence-to-sequence tasks such as machine translation and text summarization. Moreover, the success of this attention mechanism led to the seminal paper, "Attention Is

Data Science

Managing your machine learning infrastructure as code with Terraform

Let's say you want to deploy a recommender system at your company. A typical architecture might include a set of inference servers to run your embedding and ranking models, an approximate nearest neighbor index to select a set of candidate items that match your query, a database to retrieve features

Data Science

Terraform configuration: quick reference

This page contains a quick reference for writing Terraform configuration.

Data Science

A simple solution for monitoring ML systems.

This blog post aims to provide a simple, open-source solution for monitoring ML systems. We'll discuss industry-standard monitoring tools and practices for software systems and how they can be adapted to monitor ML systems.

Data Science

Effective testing for machine learning systems.

In this blog post, we'll cover what testing looks like for traditional software development, why testing machine learning systems can be different, and discuss some strategies for writing effective tests for machine learning systems. We'll also clarify the distinction between the closely related

Data Science

An introduction to Kubernetes.

This blog post will provide an introduction to Kubernetes so that you can understand the motivation behind the tool, what it is, and how you can use it. In a follow-up post, I'll discuss how we can leverage Kubernetes to power data science workloads using more concrete (data science) examples.

Data Science

Building machine learning products: a problem well-defined is a problem half-solved.

Previously, I wrote about organizing machine learning projects where I presented the framework that I use for building and deploying models. However, that framework operates on the implicit assumption that you already know generally what your model should do.

Data Science

Introduction to recurrent neural networks.

In this post, I'll discuss a third type of neural networks, recurrent neural networks, for learning from sequential data. For some classes of data, the order in which we receive observations is important. As an example, consider the two following sentences:

Data Science

Scaling nearest neighbors search with approximate methods.

In this blog post, I'll cover a couple of techniques used for approximate nearest neighbors search. This post will not cover approximate nearest neighbors methods exhaustively, but hopefully you'll be able to understand how people generally approach this problem and how to apply these techniques

Data Science

Organizing machine learning projects: project management guidelines.

The goal of this document is to provide a common framework for approaching machine learning projects that can be referenced by practitioners. If you build ML models, this post is for you.

Data Science

An overview of object detection: one-stage methods.

In this post, I'll discuss an overview of deep learning techniques for object detection using convolutional neural networks. Object detection is useful for understanding what's in an image, describing both what is in an image and where those objects are found.

Data Science

Evaluating image segmentation models.

When evaluating a standard machine learning model, we usually classify our predictions into four categories: true positives, false positives, true negatives, and false negatives. However, for the dense prediction task of image segmentation, it's not immediately clear what counts as a "true positive" and, more generally,

Data Science

An overview of semantic image segmentation.

In this post, I'll discuss how to use convolutional neural networks for the task of semantic image segmentation. Image segmentation is a computer vision task in which we label specific regions of an image according to what's being shown.

Startups

Lessons learned from attempting to launch a startup.

In Fall 2017, I made the decision to walk down the entrepreneurial path and dedicate a full-time effort towards launching a startup venture. I secured a healthy seed round of funding from a local angel investor and recruited three of my peers to join me in this effort. By Summer

Data Science

Common architectures in convolutional neural networks.

In this post, I'll discuss commonly used architectures for convolutional networks. As you'll see, almost all CNN architectures follow the same general design principles of successively applying convolutional layers to the input, periodically downsampling the spatial dimensions while increasing the number of feature maps. While the

Data Science

Variational autoencoders.

A variational autoencoder (VAE) provides a probabilistic manner for describing an observation in latent space. Thus, rather than building an encoder which outputs a single value to describe each latent state attribute, we'll formulate our encoder to describe a probability distribution

Data Science

Introduction to autoencoders.

Autoencoders are an unsupervised learning technique in which we leverage neural networks for the task of representation learning. Specifically, we'll design a neural network architecture such that we impose a bottleneck in the network which forces a compressed knowledge representation of the original input. If the input features

Data Science

Setting the learning rate of your neural network.

In previous posts, I've discussed how we can train neural networks using backpropagation with gradient descent. One of the key hyperparameters to set in order to train a neural network is the learning rate for gradient descent.

Data Science

Learning from imbalanced data.

In this blog post, I'll discuss a number of considerations and techniques for dealing with imbalanced data when training a machine learning model. The blog post will rely heavily on a sklearn contributor package called imbalanced-learn to implement the discussed techniques.

Data Science

Normalizing your data (specifically, input and batch normalization).

In this post, I'll discuss considerations for normalizing your data - with a specific focus on neural networks. In order to understand the concepts discussed, it's important to have an understanding of gradient descent.

Resolutions

New Year's Resolutions 2018

After revisiting my 2017 resolutions and evaluating how well I adhered each resolution, I'd like to set forth my resolutions for the coming year. This year, I'll set more measurable goals so that I can more effectively evaluate my performance at the end of this year.

Data Science

Hyperparameter tuning for machine learning models.

When creating a machine learning model, you'll be presented with design choices as to how to define your model architecture. Often times, we don't immediately know what the optimal model architecture should be for a given model, and thus we'd like to be able

Blockchain

What the heck is blockchain?

Lately, I've been talking more and more about blockchain and its potential impact. As I've been learning more about the technology and sharing what I've learned with my friends, I've decided it would be useful to write an introductory post to the