Much of the hype surrounding neural networks is about image-based applications. However, Recurrent Neural Networks (RNNs) have been successfully used in recent years to predict future events in time series as well. RNNs have contributed to breakthroughs in a wide variety of fields centered around predicting sequences of events. In this piece, however, we'll demonstrate how one type of RNN, the Long Short-Term Memory (LSTM) network, can be used to predict even financial time series data—perhaps the most chaotic and difficult of all time series.
This blog focuses on developing an algorithm to understand spoken Arabic digits. Such algorithms are the first step in developing computers that can understand languages with applications ranging from text-to-speech, voice-recognition, and translation, to modern AI assistants that are widely becoming available.
Artificial Intelligence (AI) is on a trajectory to become ubiquitous in every area of our lives. In this post, we explore three current applications of artificial intelligence in the real world and the machine learning techniques that make them work.
Machine vision is one of the pillars of machine learning. Its stature will grow in importance as more accurate algorithms are explored, but has already been used by Amazon for online shopping, Google for image search and Facebook for its facial recognition. Here we give a brief overview of convolutional neural networks, one of the best deep learning algorithms for image recognition.
Customer lifetime value goes a step further than churn rate prediction. It uses retention (i.e. the inverse of churn) and a “discount” factor, which accounts for the decreasing value of future money to predict the expected monetary value that a customer will generate over the entire period of the relationship with your company.
Client churn is the turnover (or attrition) rate over time of your company’s customers. Since keeping clients is often much more cost effective than finding new ones, by understanding who is likely to churn and why, we can create a cost-effective way to increase profits.
Machine Learning is still in its infancy in archaeology, but the approach holds enormous promise. Just as in finance and disaster mitigation, the use of satellite imagery has become a vital resource for archaeology. As more archaeologists around the world automate the process of identifying archaeological sites with satellite images, sites will be found at a faster rate than ever before.
We introduce the concept of Reinforcement Learning and discuss how such an algorithm can be used to solve portfolio optimizations that extract the most value from raw market data. Over time, such algorithms learn the strategies to deploy that will generate the maximum possible value and consequently the maximum possible profit.
Artificial Neural Networks were originally inspired by the human nervous system. The term has entered popular parlance in recent years due to the huge advancements in computational power and data storage abilities. We here give a brief summary of what Neural Nets are and how they work.
Document classification is currently one of the most important branches of Natural Language Processing (NLP). The general idea is to automatically classify documents into categories using machine learning algorithms.
The applications are almost endless, we can classify: patient records, movie reviews, webpages, emails (spam vs not spam), and in fact anything text based.
Relation Extraction is one of the cornerstones of Natural Language Processing and concerns the linking of two entities in unstructured text. In this blog post, we describe two of the simplest methods that are typically used: Supervised Feature Extraction and Semi-Supervised Seeding.
Dynamic Time Warping (DTW) is an intelligent, dynamically adjusted metric that allows more flexibility when used in combination with any distance dependent algorithm. This flexibility allows for better classification results in many different time-series analyses.
DTW allows us to retain the temporal dynamics by directly modeling the time-series. As its names suggests, the usual Euclidean distance in problems is replaced with a dynamically adjusted metric.
Almost every major company now has vested interest in image recognition algorithms: Tesla for autonomous driving, Amazon for product and price comparison, Google for its image search, and of course Facebook for facial recognition.
The potential for this type of technology is limitless and has already been used in fields as disparate as sport science to astronomy. Here we discuss one recent and important example in the medical field: diabetic retinopathy.
Diagnosis software, based on image recognition, allows quick and cheap diagnosis, saving human hours as well as human lives.
The goal for this project was to determine from raw neural activity what the volunteer was thinking at any given time. This form of analysis have many direct applications, for example: prosthesis moving, computer games which interface with brain activity, and even piloting vehicles without need for physical interactions.
Natural language processing has been used in speech recognition, spell-checking, document classification, and more. Moreover, it's a stepping stone to developing strong AI, one which can intelligently parse information given to it better than a human.
Recommender systems are reshaping the business world, especially E-commerce, in an unprecedented manner. They learn patterns of behaviors to predict someone's preference on a set of items they have not experienced. Over the past few years, thousands of companies have used recommender systems to help their customers find products to purchase, new movies to watch, songs to listen to, and even people they should interact with.
Properly designed multi-category patient scheduling strategy boosts service quality, operational efficiency, health outcomes and revenues and reduces costs. Our goal is to maximize the expected net revenue over a work-day, minimize the average waiting-time of patients and minimize the average number of patients who are not scanned by the end of the work-day.
Are your customers at high risk of canceling their services or changing products? Who should I target in my next ad campaign? And who are my most valuable growing client base? These are just a few of the questions that can be answered using your own, readily available, data.