Neural Nets On Spark

Nisha Muktewar and Seth Hendrickson show how to use Deeplearning4j to build deep learning models on Hadoop and Spark:

Modern convolutional networks can have several hundred million parameters. One of the top-performing neural networks in the Large Scale Visual Recognition Challenge (also known as “ImageNet”), has 140 million parameters to train! These networks not only take a lot of compute and storage resources (even with a cluster of GPUs, they can take weeks to train), but also require a lot of data. With only 30000 images, it is not practical to train such a complex model on Caltech-256 as there are not enough examples to adequately learn so many parameters. Instead, it is better to employ a method called transfer learning, which involves taking a pre-trained model and repurposing it for other use cases. Transfer learning can also greatly reduce the computational burden and remove the need for large swaths of specialized compute resources like GPUs.

It is possible to repurpose these models because convolutional neural networks tend to learn very general features when trained on image datasets, and this type of feature learning is often useful on other image datasets. For example, a network trained on ImageNet is likely to have learned how to recognize shapes, facial features, patterns, text, and so on, which will no doubt be useful for the Caltech-256 dataset.

This is a longer post, but on an extremely interesting topic.

Related Posts

KSQL Deployment Options

Hojjat Jafarpour shows us two deployment options for Kafka Streams with KSQL: As I mentioned, we have implemented KSQL on top of the Kafka Streams API. This means that every KSQL query is compiled into a Kafka Streams application. Therefore, KSQL queries follow the same execution model of Kafka Streams applications.A query can be executed […]

Read More

Reviewing Word Associations With R

Julia Silge does some exploratory analysis on the Small World of Words project: The Small World of Words project focuses on word associations. You can try it out for yourself to see how it works, but the general idea is that the participant is presented with a word (from “telephone” to “journalist” to “yoga”) and is then […]

Read More

Categories

June 2017
MTWTFSS
« May Jul »
 1234
567891011
12131415161718
19202122232425
2627282930