Gaussian graphical models [27] are a popular approach to describing networks, and are directly related to variable prediction via linear regression [20]. The focus is often on graphical model edges described by partial correlations which are zero, identifying pairs of nodes which are conditionally independent [2]. For example, the graphical LASSO [10] imposes a sparse regularization penalty on the precision matrix estimate, seeking a network which trades off predictive accuracy for sparsity. This provides a network which more interpretable and efficient to use, however it is not clear that sparse solutions actually generalize better to new data than dense solutions do [28]. Meanwhile, a different research direction is based on forming edges via some simple relationship such as affinity or univariate correlation. This limited network is used as a starting point for computing sophisticated dense estimates of relatedness between nodes, providing a deeper analysis of network structure. In such research, sparsity is usually imposed on the simple network, however the subsequent analysis is often based on methods which inherently presume Gaussian statistics and l penalties in some sense.

I've interviewed many data scientists in the last 10 years, and model explainability techniques are my favorite topic to distinguish the very best data scientists from the average. Some people think machine learning models are black boxes, useful for making predictions but otherwise unintelligible; but the best data scientists know techniques to extract real-world insights from any model. Answering these questions is more broadly useful than many people realize. This inspired me to create Kaggle's model explainability micro-course. Whether you learn the techniques from Kaggle or from a comprehensive resource like Elements of Statistical Learning, these techniques will totally change how you build, validate and deploy machine learning models.

Reinforcement learning (RL) is a general learning, predicting, and decision making paradigm. RL provides solution methods for sequential decision making problems as well as those can be transformed into sequential ones. RL connects deeply with optimization, statistics, game theory, causal inference, sequential experimentation, etc., overlaps largely with approximate dynamic programming and optimal control, and applies broadly in science, engineering and arts. RL has been making steady progress in academia recently, e.g., Atari games, AlphaGo, visuomotor policies for robots. RL has also been applied to real world scenarios like recommender systems and neural architecture search. See a recent collection about RL applications.

The field of machine ethics is concerned with the question of how to embed ethical behaviors, or a means to determine ethical behaviors, into artificial intelligence (AI) systems. The goal is to produce artificial moral agents (AMAs) that are either implicitly ethical (designed to avoid unethical consequences) or explicitly ethical (designed to behave ethically). Van Wynsberghe and Robbins' (2018) paper Critiquing the Reasons for Making Artificial Moral Agents critically addresses the reasons offered by machine ethicists for pursuing AMA research; this paper, co-authored by machine ethicists and commentators, aims to contribute to the machine ethics conversation by responding to that critique. The reasons for developing AMAs discussed in van Wynsberghe and Robbins (2018) are: it is inevitable that they will be developed; the prevention of harm; the necessity for public trust; the prevention of immoral use; such machines are better moral reasoners than humans, and building these machines would lead to a better understanding of human morality. In this paper, each co-author addresses those reasons in turn. In so doing, this paper demonstrates that the reasons critiqued are not shared by all co-authors; each machine ethicist has their own reasons for researching AMAs. But while we express a diverse range of views on each of the six reasons in van Wynsberghe and Robbins' critique, we nevertheless share the opinion that the scientific study of AMAs has considerable value.

It's 2019 and AI is well past the hype phase. The technology has advanced, with faster computing chips, smaller form factors, and improved power efficiency. As a result, there has been explosive growth in online AI training courses to get developers and data scientists started and advance their skills. Inboxes now flood with invitations to the newest AI conferences you "must attend." They offer a chaos of information on the newest advancements and resources to stay up to date.

Bias in AI is a truly worrisome issue. We've seen algorithms that are racist, sexist, and every other negative -ist you can think of. Even more troubling: if we eliminate all the human bias in our training data, an AI might still learn to be bigoted all on its own. That's a concern researchers across the world are grappling with as we move toward a future in which AI is everywhere. One bright spot: Google, a leader in AI tech, just added an AI fairness module to its crash course on machine learning.

Organizations in every industry are rapidly embracing artificial intelligence (AI) to enable and accelerate their business transformation -- with machine learning proving to be foundational to gaining insights - fueled by data. With the advent of GPU-accelerated data science businesses are realizing faster time-to-insight, making organizations more productive and cost-efficient, gaining competitive advantage. Capital One is one such business that has integrated AI and machine learning at scale, even developing its own Machine Learning Center of Excellence, an in-house consolidation of expertise and technology that enables the financial services giant to expand innovation across many businesses. Senior director Zach Hanif shares his insights on what every business should know as they seek to tap into the power of AI and machine learning. Data is the lifeblood of machine learning efforts.

In this latest Data Science Central Deep Learning Fundamentals Series webinar, we will cover the fundamentals behind TensorFlow and how to apply them within a convolutional neural network (CNN) example. The principles we will cover include CNN concepts and their impact to the accuracy and loss of your network. All these concepts will be brought to life by demonstrating how Databricks simplifies deep learning - letting you quickly access ready-to-use ML environments, as well as prepare data, and train models faster. After this session, if requested, you will receive the presentation and associated notebooks so you can run the samples yourself.

The course "Machine Learning Basics: Building a Regression model in R" teaches you all the steps of creating a Linear Regression model, which is the most popular Machine Learning model, to solve business problems. Machine Learning is a field of computer science which gives the computer the ability to learn without being explicitly programmed. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention. What is the Linear regression technique of Machine learning? Linear Regression is a simple machine learning model for regression problems, i.e., when the target variable is a real value.

Affective Computing is a rapidly growing field spurred by advancements in artificial intelligence, but often, held back by the inability to translate psychological theories of emotion into tractable computational models. To address this, we propose a probabilistic programming approach to affective computing, which models psychological-grounded theories as generative models of emotion, and implements them as stochastic, executable computer programs. We first review probabilistic approaches that integrate reasoning about emotions with reasoning about other latent mental states (e.g., beliefs, desires) in context. Recently-developed probabilistic programming languages offer several key desidarata over previous approaches, such as: (i) flexibility in representing emotions and emotional processes; (ii) modularity and compositionality; (iii) integration with deep learning libraries that facilitate efficient inference and learning from large, naturalistic data; and (iv) ease of adoption. Furthermore, using a probabilistic programming framework allows a standardized platform for theory-building and experimentation: Competing theories (e.g., of appraisal or other emotional processes) can be easily compared via modular substitution of code followed by model comparison. To jumpstart adoption, we illustrate our points with executable code that researchers can easily modify for their own models. We end with a discussion of applications and future directions of the probabilistic programming approach.