Using GPUs (Graphical Processing Units) for Machine Learning

BY

You are probably familiar with Nvidia as they have been developing graphics chips for laptops and desktops for many years now. But the company has found a new application for its graphic processing units (GPUs): machine learning. It is called CUDA. Nvidia says: "CUDA® is a parallel computing platform and programming model invented by NVIDIA. It … [Read more...]

Introduction to Neural Networks Part II

BY

In the previous post we introduced the concept of perceptrons, which take inputs from simple linear equations and output 1 (true) or 0 (false). They are the left-hand side of the neural network. But as Michael Nielsen explains, in his book, perceptrons are not suitable for tasks like image recognition because small changes to the weights and … [Read more...]

What is a Neural Network? Introduction to Neural Networks Part I

BY

We want to explore machine learning on a deeper level by discussing neural networks. We will do that by explaining how you can use Tensor Flow to recognize handwriting. But to do that we first must understand what are neural networks. We begin our discussion, based upon our knowledge of linear models, and draw some introductory material from … [Read more...]

Introduction to TensorFlow and Logistic Regression

BY

Here we introduce TensorFlow, an opensource machine learning library developed by Google. We explain what it does and show how to use it to do logistic regression. Background TensorFlow has many applications to machine learning, including neural networks. One application of neural networks is handwriting analysis. Another is facial recognition. … [Read more...]

Working with MongoDB Aggregate Functions

BY

This is the second part of the tutorial on how to use NodeJS with MongoDB. Here we switch to using the regular MongoDB shell and commands to make the study of aggregate functions simpler. To show how to use aggregate functions, we will first explain how to do basic queries. Then we will show how to do the WordCount program, which is what people … [Read more...]

MongoDB Sharding Explained

BY

MongoDB is designed to be scalable, meaning you can run it in a cluster across a distributed platform. That is called sharding. You assign different parts of the data to different servers using an index.  For example, records with the index customers could be on one set of servers and vendors on the other.  But if you want a completely random … [Read more...]

How to Use Mongoose for MongoDB and NodeJS

BY

Here we show how to use Mongoose to save data to a MongoDB. This is a two part blog post. In the second post, we will show how to run aggregation functions. The last previous post was an intro to MongoDB, so read that first. Mongoose In this example, we will use NodeJS. Do not worry if you do not know NodeJS. We will explain every line of code. … [Read more...]

MongoDB Overview: Getting Started with MongoDB

BY
ITOps, DevOps, NoOps, and more

Here we provide an overview of the MongoDB database. In subsequent posts we will give more in depth examples of how to use MongoDB. First, MongoDB is a noSQL big data database. It fits the definition of big data, because it scales (i.e., can be made larger) simply by adding more servers to a distributed system. And it is does not require any … [Read more...]