Spark Summit Europe took place in Brussels, Belgium just about a week ago. I had a pleasure to be there for conference days where I attended mostly Data Science track, as this is our bread and butter in Semantive. This summit could be summarized in a couple of words: Spark 2.0 and Streaming, as it …
Recurrent neural networks While feedforward neural networks can handle some tasks quite well, their application is limited when it comes to sequence learning. Recurrent neural networks are much more well suited for such tasks, as connections between their units form a direct cycle. This feature (sort of memory) enables RNNs to perform sequence learning and …
In this article I want to show how Apache Spark can be used to classify human activity based on smartphone data. We will build and train two simple multi-label classifiers using decision trees and random forests. Dataset We will use the Human Activity Recognition Using Smartphones Data Set provided by the UC Irvine Machine Learning …
We have been using AngularJS framework in our projects for quite a long time. It really simplifies the DOM manipulation thanks to it’s two-way data binding, offers great flexibility and makes structuring the app easy. It also has a really huge community support. Recently our client decided to switch from plain JavaScript to TypeScript in …
Deeplearning4j Deepearning4j is an open-source deep learning library written in Java and designed to be used in business environments. The tool can be easily integrated with GPU and scaled on Hadoop or Spark. As the documentation says, Deeplearning4j offers support for majority of deep architectures: Convolutional Neural Networks Restricted Boltzmann Machines Recurrent Nets Deep Belief …
What is deep learning? In recent years deep learning has gained an increasing popularity among machine learning practitioners and researchers. Google Trends shows that tendency: What is is and why it is so interesting? Basically, deep learning is an umbrella term for a whole set of advanced algorithms based usually on neural networks that consist …
I needed to concatenate multiple WAV files into one, compressed file. After searching Android API I came up with a solution using MediaMuxer, MediaCodec and MediaFormat (available since Android API 18). The code and API is relatively simple, yet useful. Basically, you have to intilialize encoder with desired parameters and feed it with PCM input …
Recently, we have been working on an Android project in which we needed audio data visualisation. After doing some research, I found an open source project called Ringdroid, which among many other features offered great waveform visualisation. As I didn’t want to reinvent the wheel and Ringdroid perfectly suited my needs, I decided to adapt …
The analysis of large data sets is becoming increasingly popular and important tool for acquiring new information in research and business. Google Trends show that tendency in time: Data Science is developing as well, using the Big Data’s growth, but with less interest in statistics software overall. This fact may have three reasons: Many of …
It’s our great pleasure to announce that we’ve become a DataStax partner – the industry leader in developing solutions based on the commercially supported, enterprise-ready Apache Cassandra. DataStax’s solutions power the mission-critical big data applications that transform business operations and enable life-changing customer experiences for some of the world’s most innovative companies, including 20 of …
