As more and more industries bring ML use cases to production, the need for consistent practices for managing ML in Production and optimizing ML Lifecycle iteration has grown rapidly. Last year, a few of us partnered with USENIX to drive the first-ever Industry/Academic conference dedicated to the challenges of and innovations in managing ML in Production. OpML 2019 was a great success - bringing together experts, practitioners, engineers, and researchers to discuss the latest and greatest in ML Ops. You can find a summary of OpML 2019 here. This year, due to COVID19, OpML 2020 became a virtual conference with video presentations and open discussions on Slack.

To talk about Reasoning, it's important to understand how we got here. This article covers what I call the pre-history of Classical AI -- those parts of the story that happened before the invention of modern computers (pre 1950s) but are crucial to understanding why we believe that AI is possible. This is part 2 in a series on Reasoning. Like most things, the very beginnings of classical AI is rooted in philosophy, and starts in the ancient world (the Greeks, Indians, and Chinese all had some early forms of logic). But, as I'm not a masochist we start in more contemporary times with two big ideas that lay the foundation for modern AI: The development of logic was humanity's first great attempt at mechanizing intelligence, and the basis for modern logic lies with George Boole, Charles Pierce, and Gottlob Frege.

This primer explores the exciting subject of intelligence. Intelligence is a fundamental component of all living things, as well as Artificial Intelligence(AI). Artificial Intelligence has the potential to affect all of our lives and a new era for modern humans. This paper is an attempt to explore the ideas associated with intelligence, and by doing so understand the implications, constraints, and potentially the capabilities of future Artificial Intelligence. As an exploration, we journey into different parts of intelligence that appear essential. We hope that people find this useful in determining where Artificial Intelligence may be headed. Also, during the exploration, we hope to create new thought-provoking questions. Intelligence is not a single weighable quantity but a subject that spans Biology, Physics, Philosophy, Cognitive Science, Neuroscience, Psychology, and Computer Science. Historian Yuval Noah Harari pointed out that engineers and scientists in the future will have to broaden their understandings to include disciplines such as Psychology, Philosophy, and Ethics. Fiction writers have long portrayed engineers and scientists as deficient in these areas. Today, modern society, the emergence of Artificial Intelligence, and legal requirements all act as forcing functions to push these broader subjects into the foreground. We start with an introduction to intelligence and move quickly onto more profound thoughts and ideas. We call this a Life, the Universe and Everything primer, after the famous science fiction book by Douglas Adams. Forty-two may very well be the right answer, but what are the questions?

Task oriented Dialogue Systems generally employ intent detection systems in order to map user queries to a set of pre-defined intents. However, user queries appearing in natural language can be easily ambiguous and hence such a direct mapping might not be straightforward harming intent detection and eventually the overall performance of a dialogue system. Moreover, acquiring domain-specific clarification questions is costly. In order to disambiguate queries which are ambiguous between two intents, we propose a novel method of generating discriminative questions using a simple rule based system which can take advantage of any question generation system without requiring annotated data of clarification questions. Our approach aims at discrimination between two intents but can be easily extended to clarification over multiple intents. Seeking clarification from the user to classify user intents not only helps understand the user intent effectively, but also reduces the roboticity of the conversation and makes the interaction considerably natural.

Wikidata constraints, albeit useful, are represented and processed in an incomplete, ad hoc fashion. Constraint declarations do not fully express their meaning, and thus do not provide a precise, unambiguous basis for constraint specification, or a logical foundation for constraint-checking implementations. In prior work we have proposed a logical framework for Wikidata as a whole, based on multi-attributed relational structures (MARS) and related logical languages. In this paper we explain how constraints are handled in the proposed framework, and show that nearly all of Wikidata's existing property constraints can be completely characterized in it, in a natural and economical fashion. We also give characterizations for several proposed property constraints, and show that a variety of non-property constraints can be handled in the same framework.

In computer science,artificial intelligence (AI), sometimes called machine intelligence, is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans. The term "artificial intelligence" is often used to describe machines (or computers) that mimic "cognitive"(process of thinking) functions that humans associate with the human mind, such as "learning" and "problem solving". What is, and what isn't AI? The popularity of AI in the media is in part due to the fact that people have started using the term when they refer to things that used to be called by other names. You can see almost anything from statistics and business analytics to manually encoded if-then rules called AI. Note- Suitcase Words Marvin Minsky, a cognitive scientist and one of the greatest pioneers in AI, coined the term suitcase word for terms that carry a whole bunch of different meanings that come along even if we intend only one of them.

Multi-attributed relational structures (MARSs) have been proposed as a formal data model for generalized property graphs, along with multi-attributed rule-based predicate logic (MARPL) as a useful rule-based logic in which to write inference rules over property graphs. Wikidata can be modelled in an extended MARS that adds the (imprecise) datatypes of Wikidata. The rules of inference for the Wikidata ontology can be modelled as a MARPL ontology, with extensions to handle the Wikidata datatypes and functions over these datatypes. Because many Wikidata qualifiers should participate in most inference rules in Wikidata a method of implicitly handling qualifier values on a per-qualifier basis is needed to make this modelling useful. The meaning of Wikidata is then the extended MARS that is the closure of running these rules on the Wikidata data model. Wikidata constraints can be modelled as multi-attributed predicate logic (MAPL) formulae, again extended with datatypes, that are evaluated over this extended MARS.

And yet, 55% are disappointed with the results of their investment. As underwhelming as this satisfaction statistic may be, it doesn't necessarily mean that AI technology itself is at fault. Rather, misguided adoption of AI is more likely to drive disappointment. The plain fact is that implementing AI is often the workplace equivalent to using a cannon to kill a mosquito. Companies are in such haste to jump on the AI bandwagon that they forgot the most fundamental question: is it the right solution for the problem?

With the advent of Industry 4.0, Data Science and Explainable Artificial Intelligence (XAI) has received considerable intrest in recent literature. However, the entry threshold into XAI, in terms of computer coding and the requisite mathematical apparatus, is really high. For fault diagnosis of steel plates, this work reports on a methodology of incorporating XAI based insights into the Data Science process of development of high precision classifier. Using Synthetic Minority Oversampling Technique (SMOTE) and notion of medoids, insights from XAI tools viz. Ceteris Peribus profiles, Partial Dependence and Breakdown profiles have been harvested. Additionally, insights in the form of IF-THEN rules have also been extracted from an optimized Random Forest and Association Rule Mining. Incorporating all the insights into a single ensemble classifier, a 10 fold cross validated performance of 94% has been achieved. In sum total, this work makes three main contributions viz.: methodology based upon utilization of medoids and SMOTE, of gleaning insights and incorporating into model development process. Secondly the insights themselves are contribution, as they benefit the human experts of steel manufacturing industry, and thirdly a high precision fault diagnosis classifier has been developed.

The heterogeneity in recently published knowledge graph embedding models' implementations, training, and evaluation has made fair and thorough comparisons difficult. In order to assess the reproducibility of previously published results, we re-implemented and evaluated 19 interaction models in the PyKEEN software package. Here, we outline which results could be reproduced with their reported hyper-parameters, which could only be reproduced with alternate hyper-parameters, and which could not be reproduced at all as well as provide insight as to why this might be the case. We then performed a large-scale benchmarking on four datasets with several thousands of experiments and 21,246 GPU hours of computation time. We present insights gained as to best practices, best configurations for each model, and where improvements could be made over previously published best configurations. Our results highlight that the combination of model architecture, training approach, loss function, and the explicit modeling of inverse relations is crucial for a model's performances, and not only determined by the model architecture. We provide evidence that several architectures can obtain results competitive to the state-of-the-art when configured carefully. We have made all code, experimental configurations, results, and analyses that lead to our interpretations available at https://github.com/pykeen/pykeen and https://github.com/pykeen/benchmarking