Data Science Machine Learning Exploiting Text Embeddings for Industry Contexts November 14, 2017 / October 9, 2025 by adamdev From Synonyms to Object Properties Itās well known that word embeddings are excellent for finding similarities between words — specifically, synonyms. We achieve this using supervised machine learning techniques by showing a neural net a dataset of hundreds of millions of pieces of text. The algorithm looks at the context and frequency in which particular […] Read more Ā»
Business Machine Learning Making Deep Learning Practical with Smaller Datasets October 25, 2017 by adamdev At the recent VB Summit in Berkeley, Jeff Dean, Head of Google Brain discussed a popular challenge in making Deep Learning a practical solution inside the enterprise: āI would say pretty much any business that has tens or hundreds of thousands of customer interactions has enough scale to start thinking about using these sorts of […] Read more Ā»
Business Developers Machine Learning Building Better Search July 10, 2017 / October 9, 2025 by adamdev In speech and writing, how often do we use one term — and only that term — to describe an idea? For example, if you were searching through a document for information relating to a businessā current assets, looking up only ācurrent assetsā would mean that you miss out on anything discussing cash, short-term assets, […] Read more Ā»
Data Science Developers Machine Learning Tutorials Python Deep Learning Frameworks Reviewed January 31, 2017 by adamdev I recently stumbled across an old Data Science Stack Exchange answer of mine on the topic of the “Best Python library for neural networks”, and it struck me how much the Python deep learning ecosystem has evolved over the course of the past 2.5 years. The library I recommended in July 2014, pylearn2, is no […] Read more Ā»
Machine Learning TensorFlow in Practice (Video + Slides) October 4, 2016 by adamdev Last week Nathan Lintz held a workshop at the Boston Machine Learning Meetup on the basics of TensorFlow. Video and slides below. Overview TensorFlow is a wonderful tool for rapidly implementing neural networks. In this presentation, we will learn the basics of TensorFlow and show how neural networks can be built with just a few […] Read more Ā»
Machine Learning Tutorials The Simple + Practical Path to Machine Learning Capability: Models with Learned Parameters September 20, 2016 / October 9, 2025 by adamdev In part one, we showed how the machine learning process is like the scientific thinking process, and in part two, we introduced a benchmark task and showed how to get your machine learning system up and running with a simple nearest neighbors model. Now you have all the necessary parts of a machine learning system: […] Read more Ā»
Machine Learning Tutorials The Simple + Practical Path to Machine Learning Capability: A Common Benchmark Task September 7, 2016 / October 9, 2025 by adamdev 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 Ā»
Developers Machine Learning Tutorials The Simple + Practical Path to Machine Learning Capability: Motivating Background, Fundamental Concepts & Workflow August 24, 2016 / October 9, 2025 by adamdev 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 Ā»
Business Image Data Use Case Machine Learning Deep Learning in Fashion (Part 2): Matching Recommendations August 4, 2016 by adamdev Online clothing stores typically recommend products by looking at their customersā past purchases or searches, and then suggest items that look similar to those products. Perhaps thatās a good strategy when youāve only been searching for, say, a striped shirt and havenāt bought one yet. But what if youāve just bought a striped shirt — […] Read more Ā»
Business Image Data Use Case Machine Learning Deep Learning in Fashion (Part 1): Transfer Learning August 2, 2016 by adamdev Transfer learning is one of the most powerful capabilities in the deep learning toolkit because you only need “small data” as opposed toĀ “Big Data”.Ā It’s a technique that allows us to take a deep neural network trained to solve one task (like recognizing objects and logos in an image),Ā and efficiently tweak it to perform another task, […] Read more Ā»
