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

Kafka Streams Basics

Anuj Saxena walks through Kafka Streams and provides a quick example: The features provided by Kafka Streams: Highly scalable, elastic, distributed, and fault-tolerant application. Stateful and stateless processing. Event-time processing with windowing, joins, and aggregations. We can use the already-defined most common transformation operation using Kafka Streams DSL or the lower-level processor API, which allow us […]

Read More

Random Forests In R

Anish Sing Walia explains the basics of random forests and provides sample code in R: Random Forests are similar to a famous Ensemble technique called Bagging but have a different tweak in it. In Random Forests the idea is to decorrelate the several trees which are generated on the different bootstrapped samples from training Data.And […]

Read More


June 2017
« May Jul »