Artificial intelligence has been shaking up the marketing world for the last few years, helping automate menial, repetitive tasks, inform better creative decisions, and predict revenue projections. But many of the tools available for that latter category, namely, predictive analytics, have a less-than-stellar accuracy rate. South Africa-based Xineoh has developed a platform for predicting customer behavior with AI. The company claims its technolgoy is more accurate than any other solution available. Xineoh was founded in 2010 and raised $2 million from U.S. and Canadian investors in June 2017.

I was introduced to deep learning as part of Udacity's Self-Driving Car Nanodegree (SDCND) program, which I started in November. Some of our projects required building deep neural networks for tasks such as classifying traffics signs, and using behavior cloning to train a car to drive autonomously in a simulator. However, my MacBook Pro was not up to the task of training neural networks. I used AWS for my first deep learning project, and while it's a viable option, I decided to build my own machine for greater flexibility and convenience. I also plan to do a lot of deep learning outside of the nanodegree, such as Kaggle competitions and side projects, so it should end up being the more cost effective option as well.

Humans have always been thrilled with the concept of human-like robots and Artificial Intelligence (A.I.). Hollywood movies and science fiction have perhaps inspired several scientists to start working towards this direction. Although the AI bubble has burst many times, significant developments and breakthroughs are now renewing public interest in this field. In 2017, Gartner placed general AI at the stage of early adoption in its hype cycle. It also placed deep learning and machine learning technologies at the peak of this hype cycle. It is important to realize that AI is an umbrella term for several interlinked technologies.

Machine-learning technology powers many aspects of modern society: from web searches to content filtering on social networks to recommendations on e-commerce websites, and it is increasingly present in consumer products such as cameras and smartphones. Machine-learning systems are used to identify objects in images, transcribe speech into text, match news items, posts or products with users' interests, and select relevant results of search. Increasingly, these applications make use of a class of techniques called deep learning.[5] Deep learning (also known as deep structured learning, hierarchical learning or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high level abstractions in data. In a simple case, you could have two sets of neurons: ones that receive an input signal and ones that send an output signal.

Call it an a-MAZE-ing development: A U.K.-based team of researchers has developed an artificial intelligence program that can learn to take shortcuts through a labyrinth to reach its goal. In the process, the program developed structures akin to those in the human brain. The emergence of these computational "grid cells," described in the journal Nature, could help scientists design better navigational software for future robots and even offer a new window through which to probe the mysteries of the mammalian brain. In recent years, AI researchers have developed and fine-tuned deep-learning networks -- layered programs that can come up with novel solutions to achieve their assigned goal. For example, a deep-learning network can be told which face to identify in a series of different photos, and through several rounds of training, can tune its algorithms until it spots the right face virtually every time.

As a beginner at deep learning, one of the things I realized is that there isn't much online documentation that covers all the deep learning tricks in one place. There are lots of small best practices, ranging from simple tricks like initializing weights, regularization to slightly complex techniques like cyclic learning rates that can make training and debugging neural nets easier and efficient. This inspired me to write this series of blogs where I will cover as many nuances as I can to make implementing deep learning simpler for you. While writing this blog, the assumption is that you have a basic idea of how neural networks are trained. An understanding of weights, biases, hidden layers, activations and activation functions will make the content clearer.

An offspring of the Google team, Tensorflow is one of the most advanced Python frameworks for machine learning that implements deep machine learning algorithms. It is a second-generation, open-source system, the predecessor of which was the less integral recognition solution DistBelief. Despite its high learning curve, the product can nevertheless provide developers with a number of capabilities (alternatively, you can choose from other popular machine learning frameworks with steeper learning curves, like Theano). In particular, Tensorflow features tools that allow executing the input data analysis both with the help of encyclopedic data and the data previously analyzed during the interaction with certain users (supervisors). Although Tensorflow's final results are characterized by a high level of precision, developers usually prefer not to use it in scientific software development.

Deep learning has significantly improved state-of-the-art performance for natural language processing tasks like machine translation, summarization, question answering, and text classification. Each of these tasks is typically studied with a specific metric, and performance is often measured on a set of standard benchmark datasets. This has led to the development of architectures designed specifically for those tasks and metrics, but it does not necessarily promote the emergence of general NLP models, those which can perform well across a wide variety of NLP tasks. In order to explore the possibility of such models as well as the tradeoffs that arise in optimizing for them, we introduce the Natural Language Decathlon (decaNLP). The goal of the Decathlon is to explore models that generalize to all ten tasks and investigate how such models differ from those trained for single tasks.

This 7-week course is designed for anyone with at least a year of coding experience, and some memory of high-school math. You will start with step one--learning how to get a GPU server online suitable for deep learning--and go all the way through to creating state of the art, highly practical, models for computer vision, natural language processing, and recommendation systems. There are around 20 hours of lessons, and you should plan to spend around 10 hours a week for 7 weeks to complete the material. The course is based on lessons recorded during the first certificate course at The Data Institute at USF.

AI knows when you're going to die. But unlike in sci-fi movies, that information could end up saving lives. A new paper published in Nature suggests that feeding electronic health record data to a deep learning model could substantially improve the accuracy of projected outcomes. In trials using data from two U.S. hospitals, researchers were able to show that these algorithms could predict a patient's length of stay and time of discharge, but also the time of death. The neural network described in the study uses an immense amount of data, such as a patient's vitals and medical history, to make its predictions.