Explainability is essential for users to effectively understand, trust, and manage powerful artificial intelligence applications.

Recent successes in machine learning (ML) have led to a new wave of artificial intelligence (AI) applications that offer extensive benefits to a diverse range of fields. However, many of these systems are not able to explain their autonomous decisions and actions to human users. Explanations may not be essential for certain AI applications, and some AI researchers argue that the emphasis on explanation is misplaced, too difficult to achieve, and perhaps unnecessary. However, for many critical applications in defense, medicine, finance, and law, explanations are essential for users to understand, trust, and effectively manage these new, artificially intelligent partners [see recent reviews (1–3)].

Recent AI successes are largely attributed to new ML techniques that construct models in their internal representations. These include support vector machines (SVMs), random forests, probabilistic graphical models, reinforcement learning (RL), and deep learning (DL) neural networks. Although these models exhibit high performance, they are opaque in terms of explainability. There may be inherent conflict between ML performance (e.g., predictive accuracy) and explainability. Often, the highest performing methods (e.g., DL) are the least explainable, and the most explainable (e.g., decision trees) are the least accurate. Figure 1 illustrates this with a notional graph of the performance-explainability tradeoff for some of the ML techniques. Read More

Systems built around AI will affect and, in many cases, redefine medical interventions, autonomous transportation, criminal justice, financial risk management and many other areas of society.However, considering the challenges , the usefulness and fairness of these AI systems will be gated by our ability to understand, explain and control them. Read More

#explainability

June marked the first anniversary of Google’s AI Principles, which formally outline our pledge to explore the potential of AI in a respectful, ethical and socially beneficial way. For Google Cloud, they also serve as an ongoing commitment to our customers—the tens of thousands of businesses worldwide who rely on Google Cloud AI every day—to deliver the transformative capabilities they need to thrive while aiming to help improve privacy, security, fairness, and the trust of their users.

We strive to build AI aligned with our AI Principles and we’re excited to introduce Explainable AI, which helps humans understand how a machine learning model reaches its conclusions. Read More

Machine learning algorithms are starting to exceed human performance in many narrow and specific domains, such as image recognition and certain types of medical diagnoses. They’re also rapidly improving in more complex domains such as generating eerily human-like text. We increasingly rely on machine learning algorithms to make decisions on a wide range of topics, from what we collectively spend billions of hours watching to who gets the job.

But machine learning algorithms cannot explain the decisions they make. How can we justify putting these systems in charge of decisions that affect people’s lives if we don’t understand how they’re arriving at those decisions? Read More

Even as machines known as “deep neural networks” have learned to converse, drive cars, beat video games and Go champions, dream, paint pictures and help make scientific discoveries, they have also confounded their human creators, who never expected so-called “deep-learning” algorithms to work so well. No underlying principle has guided the design of these learning systems, other than vague inspiration drawn from the architecture of the brain (and no one really understands how that operates either).

… Last month, a YouTube video of a conference talk in Berlin, shared widely among artificial-intelligence researchers, offered a possible answer. In the talk, Naftali Tishby, a computer scientist and neuroscientist from the Hebrew University of Jerusalem, presented evidence in support of a new theory explaining how deep learning works. Read More

#explainability

Nowadays, artificial intelligence is present in almost every part of our lives. Smartphones, social media feeds, recommendation engines, online ad networks, and navigation tools are some examples of AI-based applications that already affect us every day. Deep learning in areas such as speech recognition, autonomous driving, machine translation, and visual object recognition has been systematically improving the state of the art for a while now.

However, the reasons that make deep neural networks (DNN) so powerful are only heuristically understood, i.e. we know only from experience that we can achieve excellent results by using large datasets and following specific training protocols. Recently, one possible explanation was proposed, based on a remarkable analogy between a physics-based conceptual framework called renormalization group (RG) and a type of neural network known as a restricted Boltzmann machine (RBM). Read More

#explainability