We know Grakn can be leveraged to model highly complex data, but how do we go about building a detailed model of a real-world system?
Here, we delve into Transport for London (TFL) data to understand and gain insights into the operation of the London Underground Network.
We go on to build surely the most desirable tool for such a network: a journey planner. (Because who doesn’t want to shave 0.3 minutes off their commute?)
About a year ago, I was convinced that the key to succeeding with Artificial Intelligence (AI) was to take a platform approach. In other words, the synergies that accrue from appropriately bringing together the range of technologies that are making AI a reality for enterprises was, I believed, the way to go. I still firmly believe that.
In fact, having personally met over 200 executives (business and technology) since then, from around the world, who seek to find relief and new value from AI, I am convinced that opting for best of breed capabilities from a variety of vendors is not necessarily going to work out in practice. For one, despite claims of using only open standards in building these offerings, deploying the offerings from a variety of vendors in an integrated manner is a challenge. Further, the business and operational challenges that naturally occur in such situations with multiple providers are deterrents too.
Back in November last year, Forrester posted an article with a stark warning: "AI hard-fact — treat it like a plug-and-play panacea and fail." The hype surrounding Artificial Intelligence (AI) has only grown since then.
Today, a cursory Google search of the term "AI" results in 2.4 billion entries. That’s a lot of AI chatter! While a Google search may be a blunt instrument for measuring the true impact of AI, it does illustrate just how "big" it has grown. If your inbox is anything like mine, I’m sure you’re only too aware that AI-everything is being used to solve AI-anything. That is exactly why Forrester’s prediction was so apt.
The days of leaving Slack to create an event on your calendar are over!
In this tutorial, you are going to learn how to create a scheduler bot that adds events to your personal calendar with a simple Slack slash command using the Nylas Calendar API.
At Grakn, we recently released Grakn 1.3, with a slew of new features, bug fixes, and performance enhancements. Included in this release are new gRPC-based drivers for Java, NodeJS, and Python. This article will walk you through the Python driver and provide guidelines on how you can write your own for your language of choice.
The main reason for rewriting our drivers was a move from REST to gRPC in Grakn. This change has cleaned up our API and should provide performance benefits. Further, all of our available drivers (Java, Node, and Python) now expose the same objects and methods to users, subject to language naming conventions and available types. To maintain this uniformity across the stack, new language drivers should provide the same interface. Note that you will require both gRPC and protobuf support to create a functioning driver, so double check a) that compilers for your language exist, and b) your target language version is compatible with the compiler.
According to Gartner, smart cities will be using about 1.39 billion connected cars, IoT sensors, and devices by 2020. The analysis of location and behavior patterns within cities will allow optimization of traffic, better planning decisions, and smarter advertising. For example, the analysis of GPS car data can allow cities to optimize traffic flows based on real-time traffic information. Telecom companies are using mobile phone location data to provide insights by identifying and predicting the location activity trends and patterns of a population in a large metropolitan area. The application of Machine Learning to geolocation data is being used in telecom, travel, marketing, and manufacturing to identify patterns and trends for services such as recommendations, anomaly detection, and fraud.
In this article, we discuss using Spark Structured Streaming in a data processing pipeline for cluster analysis on Uber event data to detect and visualize popular Uber locations.
Machine vision, or computer vision, is a popular research topic in artificial intelligence (AI) that has been around for many years. However, machine vision still remains as one of the biggest challenges in AI. In this article, we will explore the use of deep neural networks to address some of the fundamental challenges of computer vision. In particular, we will be looking at applications such as network compression, fine-grained image classification, captioning, texture synthesis, image search, and object tracking.
Even though deep neural networks feature incredible performance, their demands for computing power and storage pose a significant challenge to their deployment in actual application. Research shows that the parameters used in a neural network can be hugely redundant. Therefore, a lot of work is put into increasing accuracy while also decreasing the complexity of the network.
In this article, we will study a comparison between Deep Learning and Machine Learning. We will also learn about them individually. We will also cover their differences on various points. Along with a Deep Learning and Machine Learning comparison, we will also study their future trends.
Generally, to implement Artificial Intelligence, we use Machine Learning. We have several algorithms that are used for Machine Learning. For example:
The confusion matrix is one of the most popular and widely used performance measurement techniques for classification models. While it is super easy to understand, its terminology can be a bit confusing.
Therefore, keeping the above premise under consideration, this article aims to clear the "fog" around this amazing model evaluation system.
In this post, you will learn about different types of test cases that you could come up for testing features of the Data Science/Machine Learning models. Testing features are one of the key sets of which needs to be performed for ensuring the high performance of Machine Learning models in a consistent and sustained manner.
Features make the most important part of a Machine Learning model. Features are nothing but the predictor variable, which is used to predict the outcome or response variable. Simply speaking, the following function represents y as the outcome variable and x1, x2, and x1x2 as predictor variables.
