Collaborating Authors

Forecasting air quality with Dremio, Python and Kafka


Forecasting air quality is a worthwhile investment on many different levels, not only to individuals but also communities in general, having an idea of what the quality of air will be at a certain point in time allows people to plan ahead, and as a result decreases the effects on health and costs associated with it. When predicting air quality, there is a large number of variables to take into account, using a machine learning model that allows us to use all these variables to predict future air quality based on current readings, brings a lot of value to the scenario. In this tutorial, we will create a machine learning model using historical air quality data stored in Amazon S3 buckets and also ADLS, we will use Dremio to link both data sources and also curate the data before creating the model using Python, additionally we will use the resulting model along with Kafka to predict air quality values to a data stream. In Amazon S3 the data should be stored inside buckets. To create a bucket (we want to call it (dremioairbucket), go to the AWS portal and select S3 from the list of services.

Setting up Tensorflow and GPUs on Google Cloud Platform to run your neural network implementations


After my teammates and I had completed our implementation of CycleGANs for our Computer Vision class project, we needed GPUs to run the python script containing the tensorflow code. Since we had multiple datasets, we could not run the code using a single dataset on the Blue Waters quota allotted to us and wait for it to get done. We needed more GPUs!!! So, while my teammates were involved in running it on Blue Waters, I decided to give Google Cloud Platform a try. After going through multiple blogs and tutorials to set up GPUs and tensorflow on Google Cloud, I realized that none of them would give me all the details in one place and therefore, I was compelled to write this blog to provide a step by step procedure on how to set up GPUs and tensorflow on Google Cloud Platform from start to finish. So lets get right to it.

Understanding neural networks with TensorFlow Playground Google Cloud Big Data and Machine Learning Blog Google Cloud Platform


This is how simple neurons get smarter and perform so well for certain problems such as image recognition and playing Go. Inception: an image recognition model published by Google (From: Going deeper with convolutions, Christian Szegedy et al.) Some published examples of visualization by deep networks show how they're trained to build the hierarchy of recognized patterns, from simple edges and blobs to object parts and classes. In this article, we looked at some TensorFlow Playground demos and how they explain the mechanism and power of neural networks. As you've seen, the basics of the technology are pretty simple.

Photoshop Styles: What they are and how to use them


Photoshop styles are works of art that can be applied to text, objects, vector shapes, illustrations, or photos. Unlike Microsoft styles, which are basically just a collection of attributes (such as bold, italic, underline) and minor effects (such as shadows, reflections, glowing halos), Photoshop uses layers to contain text and images, and those layers can be "decorated" with a style. Photoshop Styles are accessed through the Styles panel, which you can add to your Photoshop desktop through the Window tab: Select Window Styles and the panel appears. I combine the Styles panel with the Layers panel and leave both open all the time. Notice that Photoshop provides 20 "free" styles in four categories (Basic, Natural, Fur, and Fabric) to get you started.

Module 20 - Building Neural Network Application Using TensorFlow engMRK


In this module, we will implement a neural network application using TensorFlow on E-commerce data set. We will predict the yearly amount spent by each customer based on their browsing behavior. The data set is already loaded in the exercises below so you just have to understand the code and run it to check the output. TensorFlow is a software framework for building and deploying machine learning models. It provides the basic building blocks to design, train, and deploy machine learning models.