Ray Bradbury and others envisioned a world in which human needs are anticipated by the surrounding environment. In the late 1990s, this vision was termed "ambient intelligence" (AmI). Since that time, innovators have continued to imagine scenarios in which technology is ubiquitous, more transparent, and more valuable to humans than it ever has been. What the user interface will ultimately look like is a matter of debate. Some foresee a Minority Report scenario in which the surrounding environment itself adapts to individuals in context.

I'm looking for expertise in ML (mkting/adv applications a plus) to build and test a hypothesis around the use of text classification to a taxonomy. My employer eContext, has curated a general taxonomy that encompasses everything commercially and socially relevant on the web. It consists of 650M real user search queries bucketed into 25 vertical categories (Auto, Health, Finance, etc.) containing roughly 450K sub-categories. It's a rule-based system, and we use NLP and nGram chunking to parse long and short form text and map search queries, social posts, web content, blogs, forums, etc. to the category hierarchy providing structured, topical intelligence to data streams at scale. I understand that supervised training models require a corpus of text from which a model can determine entities, ontological connections, and apply statistical models to understand what people, places, things, concepts are and how they may be connected. That said, we've already built out the taxonomy to understand those connections and can provide greater context to "what" something truly is.

The risk of cyberattacks is one of the most dangerous threats facing businesses today. And while new versions of attacks are constantly being born, teams of analysts are rushing to keep up with the latest risks. While many detection systems rely primarily on machine learning for catching attackers, a new AI system at PatternEx depends on human analysts as a vital part of their system of supervised machine learning. Humans 2.0: How the robot revolution is going to change how we see, feel, and talk Robots aren't going to replace us, but by working hand in hand with us they will redefine what it means to be human. PatternEx's AI system is the first "virtual" security analyst team, and can predict, detect, and stop attackers in real time.

It is made up of 650M real user search queries bucketed into 25 vertical categories (Auto, Health, Finance, etc.) containing roughly 450K sub-categories. It's a rule-based system, and we use NLP and nGram chunking to parse long and short form text and map search queries, social posts, web content, blogs, forums, reviews, etc. to the category hierarchy providing structured, topical intelligence to data streams at scale. It is extremely accurate because we've built 55M controlled vocabularies (Ex. Being the noob I am, I am trying to understand how our real time classification capabilities can improve the efficiency of machine learned processes. I understand that supervised training models require a corpus of text from which a model can determine entities, ontological connections, and apply statistical models to understand what people, places, things, concepts are and how they may be connected, but we've already built out the taxonomy to understand connections between things, and can provide greater context to "what" something truly is.

See machine learning in action during "A Glimpse into the Future of Email Marketing – Reaping the Benefits of Machine Learning," featuring Kath Pay, Dela Quist, Skip Fidura and Jeremy Swift, May 19 at the Email Innovations Summit in Las Vegas. "Machine learning" has moved out of science fiction and into real-life applications, like powering Tesla cars that run on autopilot and robots that can beat humans at the Japanese game of Go. For marketers, it gets them closer to their email nirvana: true 1:1 personalization on a mass scale. Machine learning, at its simplest, is a method of data analysis that allows computers to learn – to analyze, predict and act – without explicit instructions or programming. That last phrase – "without explicit instructions or programming" – highlights the difference between today's rule-based marketing automation and systems that use machine learning.

Spam is a kind of messaging where the cost of sending is usually negligible and the receiver and the ISP pays the cost in terms of bandwidth usage. An example of a manual approach to detecting spam is using knowledge engineering. If the subject line of an email contains words'Buy viagra' its spam These rules can be configured by the user himself or by the email provider and if correctly thought out and executed this technique can be effectively be used to combat spam. This is a blog post about one such implementation. However, a manual rules based approach doesn't scale because of active human spammers circumventing any manual rules.

The study of cellular signalling pathways and their deregulation in disease states, such as cancer, is a large and extremely complex task. Indeed, these systems involve many parts and processes but are studied piecewise and their literatures and data are consequently fragmented, distributed and sometimes--at least apparently--inconsistent. This makes it extremely difficult to build significant explanatory models with the result that effects in these systems that are brought about by many interacting factors are poorly understood. The rule-based approach to modelling has shown some promise for the representation of the highly combinatorial systems typically found in signalling where many of the proteins are composed of multiple binding domains, capable of simultaneous interactions, and/or peptide motifs controlled by post-translational modifications. However, the rule-based approach requires highly detailed information about the precise conditions for each and every interaction which is rarely available from any one single source. Rather, these conditions must be painstakingly inferred and curated, by hand, from information contained in many papers--each of which contains only part of the story. In this paper, we introduce a graph-based meta-model, attuned to the representation of cellular signalling networks, which aims to ease this massive cognitive burden on the rule-based curation process. This meta-model is a generalization of that used by Kappa and BNGL which allows for the flexible representation of knowledge at various levels of granularity. In particular, it allows us to deal with information which has either too little, or too much, detail with respect to the strict rule-based meta-model. Our approach provides a basis for the gradual aggregation of fragmented biological knowledge extracted from the literature into an instance of the meta-model from which we can define an automated translation into executable Kappa programs.

Capturing domain knowledge can be a time-consuming process that typically requires the collaboration of a Subject Matter Expert and a modeling expert to encode the knowledge. In a number of domains and applications, this situation is further exacerbated by the fact that the Subject Matter Expert may find it difficult to articulate the domain knowledge as a procedure or rules, but instead may find it easier to classify instance data. To facilitate this type of knowledge elicitation from Subject Matter Experts, we have developed a system that automatically generates formal and executable rules from provided labeled instance data. We do this by leveraging the techniques of Inductive Logic Programming (ILP) to generate Horn clause based rules to separate out positive and negative instance data. We illustrate our approach on a Design For Manufacturability (DFM) platform where the goal is to design products that are easy to manufacture by providing early manufacturability feedback. Specifically we show how our approach can be used to generate feature recognition rules from positive and negative instance data supplied by Subject Matter Experts. Our platform is interactive, provides visual feedback and is iterative. The feature identification rules generated can be inspected, manually refined and vetted.

Action languages have emerged as an important field of Knowledge Representation for reasoning about change and causality in dynamic domains. This article presents Cerbere, a production system designed to perform online causal, temporal and epistemic reasoning based on the Event Calculus. The framework implements the declarative semantics of the underlying logic theories in a forward-chaining rule-based reasoning system, coupling the high expressiveness of its formalisms with the efficiency of rule-based systems. To illustrate its applicability, we present both the modeling of benchmark problems in the field, as well as its utilization in the challenging domain of smart spaces. A hybrid framework that combines logic-based with probabilistic reasoning has been developed, that aims to accommodate activity recognition and monitoring tasks in smart spaces. Under consideration in Theory and Practice of Logic Programming (TPLP)

We aim to produce predictive models that are not only accurate, but are also interpretable to human experts. Our models are decision lists, which consist of a series of if...then... statements (e.g., if high blood pressure, then stroke) that discretize a high-dimensional, multivariate feature space into a series of simple, readily interpretable decision statements. We introduce a generative model called Bayesian Rule Lists that yields a posterior distribution over possible decision lists. It employs a novel prior structure to encourage sparsity. Our experiments show that Bayesian Rule Lists has predictive accuracy on par with the current top algorithms for prediction in machine learning. Our method is motivated by recent developments in personalized medicine, and can be used to produce highly accurate and interpretable medical scoring systems. We demonstrate this by producing an alternative to the CHADS$_2$ score, actively used in clinical practice for estimating the risk of stroke in patients that have atrial fibrillation. Our model is as interpretable as CHADS$_2$, but more accurate.