A Hacker’s Guide to Efficiently Train Deep Learning Models

A Hacker’s Guide to Efficiently Train Deep Learning Models

  • May 7, 2020
Table of Contents

A Hacker’s Guide to Efficiently Train Deep Learning Models

Three months ago, I participated in a data science challenge that took place at my company. The goal was to help a marine researcher better identify whales based on the appearance of their flukes. More specifically, we were asked to predict for each image of a test set, the top 20 most similar images from the full database (train+test).

This was not a standard classification task. I spent 3 months prototyping and ended up third at the final (private) leaderboard. But let’s not enter the specifics of this challenge.

The purpose of this post is to share with you my tips on building strong embedding models for visual similarity tasks. This challenge was a superb learning opportunity where I tried a lot of different techniques. So I’ll share with you here what best worked and what did not, and I’ll detail the different steps I undertook in the process.

Source: medium.com

Tags :
Share :
comments powered by Disqus

Related Posts

MIT CSAIL TextFooler Framework Tricks Leading NLP Systems

MIT CSAIL TextFooler Framework Tricks Leading NLP Systems

A team of researchers at the MIT Computer Science & Artificial Intelligence Lab (CSAIL) recently released a framework called TextFooler which successfully tricked state-of-the-art NLP models (such as BERT) into making incorrect predictions.

Read More
Deep Learning for Anomaly Detection

Deep Learning for Anomaly Detection

Anomalies, often referred to as outliers, are data points or patterns in data that do not conform to a notion of normal behavior. Anomaly detection, then, is the task of finding those patterns in data that do not adhere to expected norms. The capability to recognize or detect anomalous behavior can provide highly useful insights across industries.

Read More
When machine learning packs an economic punch

When machine learning packs an economic punch

A new study co-authored by an MIT economist shows that improved translation software can significantly boost international trade online — a notable case of machine learning having a clear impact on economic activity. The research finds that after eBay improved its automatic translation program in 2014, commerce shot up by 10.9 percent among pairs of countries where people could use the new system. To put the results in perspective, he adds, consider that physical distance is, by itself, also a significant barrier to global commerce.

Read More