This is the second post in a series of me trying to learn something new over a short period of time. The first time consisted of learning how to do machine learning in a week. This time I've tried to learn neural networks. While I didn't manage to do it within a week, due to various reasons, I did get a basic understanding of it throughout the summer and autumn of 2015. By basic understanding, I mean that I finally know how to code simple neural networks from scratch on my own.

This is the third in a series of reports to document development of a generalized method to create artificial neural networks (ANNs) via a genetic algorithm (GA). This report will be divided into several main sections. The goal of this report is to demonstrate the ability of an ANN to recognize letters by providing example images to the ANN. It will use those images as a training set to recognize letters in a street sign. Report 2 introduced image processing so that image data can be submitted to the ANN for pattern recognition.

We expected so much from "a technology platform that uses natural language processing and machine learning to reveal insights from large amounts of unstructured data." And what did we get? @!!@# Granola. Bear Naked Granola uses Watson to make custom suggestions for mixing your own granola which they will then ship to your door, ten bucks for ten ounces. At first glance, it sounds like an idiotic waste of resources. After all, 50 ingredients is not exactly a large amount of unstructured data.

When you are performing with Caffe, you need to determine your deep neural network architecture in a '.prototxt' file. These prototxt information ordinarily consist of hundreds of strains, defining layers and corresponding parameters. Before you commence schooling your neural network, you need to produce these information and determine your architecture. But from time to time, it's useful to dynamically produce this architecture depending on our wants. In this sort of circumstances, producing a deep neural network programmatically can be really valuable.

One key buzzword these days is "algorithm," which technically means any computational formula but which has come to mean a formula that predicts our behavior. Amazon and Netflix have algorithms that predict what books a user is likely to want to read or what movies and TV shows he or she is likely to want to watch. Facebook has an algorithm that predicts the news a user is likely to want. Dating sites like Match.com and OkCupid use algorithms to predict with whom we would fall in love. Google, with the most famous algorithm of all, predicts what we want when we type a search term.

It's hard to find someone who isn't a fan of "Game of Thrones." The TV show, which returns Sunday, has reached peaks of popularity that few shows do, and draws in fans of all shapes and sizes -- even computers. Maluuba, a Canadian startup, posted a YouTube video on Friday showing its artificial-intelligence software reading the synopsis for the fifth season of "Game of Thrones'" and immediately knowing all of the show's plot lines. It's the equivalent to a human, let's call him "John" for this example, who knows nothing about the show, has never seen it, takes one look at a Wikipedia page and instantaneously knows everything that's happening. "Who stabbed Jon Snow?" the Maluuba engineer asks the AI software.

This is the first in a series of reports to document development of a generalized method to create artificial neural networks (ANNs) via a genetic algorithm (GA). This report will be divided into several main sections. The goal of this project is to develop a library of ANNs that can be used to resolve a variety of problems. The initial development goal is to demonstrate its viability by accurately distinguishing between women and men when provided key facial data. Due to the generalized nature of the ANN creation process it should be straight forward to train a number of specialized ANNs.

A data scientist is one of the most in-demand, high-profile careers in IT today, but Tom Walsh and Alex Krowitz have been working behind the scenes in the field for years. Walsh, a research engineer and Krowitz, a senior research engineer at cloud workforce management solutions company Kronos, sift through the influx of proprietary and customer data to identify patterns and gain insights based on that data. There are generally two kinds of projects we regularly handle; mining patterns within data to improve our own products is one and the other is taking on specific sets of customer data to gather and deliver insights from that," says Walsh. What companies are looking for is ultimately the capability to make predictions based on that data, says Krowitz. Companies use those predictions to help drive everything from marketing strategy to resource allocation, personnel levels and staffing, or to predict retail sales, he says. "We have products that use machine learning algorithms to help customers with these predictions.

Big data can't deliver on its potential unless enterprises have the right tools to extract insights. Woodside, an Australia-based oil and gas giant, realizes this and is using advanced machine learning technology to leverage its data via predictive analysis. Front and center in the company's toolkit is IBM Watson, a cutting-edge machine learning and natural language processing platform that analyzes vast amounts of unstructured data. According to CIO, Woodside is using a variety of big data tools -- including Amazon Web Services (AWS), Apache Spark and Watson -- to improve operational efficiency and predict potential catastrophes at its production facilities. Elsa Jordan, principal data scientist at Woodside, told attendees of the Chief Analytics Officer Forum in Sydney how the company has implemented these data science technologies in recent years and how the Watson engine has become a key component of the organization's big data platform.

Even though Gilles has recently graduated with a degree in Fundamental Mathematics, he knows that there's more to be done than mathematics. With a solid knowledge in classical statistics, he now pursues a PhD in parallelizing regression modeling techniques. Vincent has just finished his Master's degree in Artificial Intelligence, and has more than 3 years of experience with machine learning problems of different kinds. He experienced first-hand the difficulties that come with building and assessing machine learning systems. This made him passionate about teaching people how to do machine learning the right way.