For text entry methods to be useful they have to deliver high entry rates and low error rates. At the same time they need to be easy-to-learn and provide effective means of correcting mistakes. Intelligent text entry methods combine AI techniques with HCI theory to enable users to enter text as efficiently and effortlessly as possible. Here I sample a selection of such techniques from the research literature and set them into their historical context. I then highlight five challenges for text entry methods that aspire to make an impact in our society: localization, error correction, editor support, feedback, and context of use.

The RADAR project developed a large multi-agent system with a mixed-initiative user interface designed to help office workers cope with email overload. Most RADAR agents observe experts performing tasks and then assist other users who are performing similar tasks. The interaction design for RADAR focused on developing user interfaces that allowed the intelligent functionality to improve the user’s workflow without frustrating the user when the system’s suggestions were either unhelpful or simply incorrect. For example with regards to autonomy, the RADAR agents were allowed much flexibility in selecting ways to assist the user, but were restricted from taking actions that would be visible to other people. This policy ensured that the user remained in control and mitigated the negative effects of mistakes. A large evaluation of RADAR demonstrated that novice users confronted with an email overload test performed significantly better, achieving a 37% better overall score when assisted by RADAR. The evaluation showed that AI technologies can help users accomplish their goals.

These unintended negative consequences of the introduction of intelligence often have no direct relationship with the intended benefits, just as the adverse effects of a medication may bear no obvious relationship to the intended benefits of taking that medicine. Therefore, these negative consequences can be seen as side effects. The purpose of this article is to give designers, developers, and users of interactive intelligent systems a detailed awareness of the potential side effects of AI. As with medications, awareness of the side effects can have different implications: We may be relieved to see that a given side effect is unlikely to occur in our particular case. We may become convinced that it will inevitably occur and therefore decide not to "take the medicine" (that is, decide to stick with mainstream systems). Or most likely and most constructively, by looking carefully at the causes of the side effects and the conditions under which they can occur, we can figure out how to exploit the benefits of AI in interactive systems while avoiding the side effects.

This is an opinion piece about the relationship between the fields of human-computer interaction (HCI), and artificial intelligence (AI). The ultimate goal of both fields is to make user interfaces more effective and easier to use for people. But historically, they have disagreed about whether "intelligence" or "direct manipulation" is the better route to achieving this. There is an unjustified perception in HCI that AI is unreliable. There is an unjustified perception in AI that interfaces are merely cosmetic. This disagreement is counterproductive.This article argues that AI's goals of intelligent interfaces would benefit enormously by the user-centered design and testing principles of HCI. It argues that HCI's stated goals of meeting the needs of users and interacting in natural ways, would be best served by application of AI. Peace.

When creating algorithms or systems that are supposed to be used by people, we should be able to adopt a “binocular” view of users’ interaction with intelligent systems: a view that regards the design of interaction and the design of intelligent algorithms as interrelated parts of a single design problem. This special issue offers a coherent set of articles on two levels of generality that illustrate the binocular view and help readers to adopt it.

A fundamental objective in reinforcement learning is the maintenance of a proper balance between exploration and exploitation. This problem becomes more challenging when the agent can only partially observe the states of its environment. In this paper we propose a dual-policy method for jointly learning the agent behavior and the balance between exploration exploitation, in partially observable environments. The method subsumes traditional exploration, in which the agent takes actions to gather information about the environment, and active learning, in which the agent queries an oracle for optimal actions (with an associated cost for employing the oracle). The form of the employed exploration is dictated by the specific problem. Theoretical guarantees are provided concerning the optimality of the balancing of exploration and exploitation. The effectiveness of the method is demonstrated by experimental results on benchmark problems.

We propose a Bayesian nonparametric approach to relating multiple time series via a set of latent, dynamical behaviors. Using a beta process prior, we allow data-driven selection of the size of this set, as well as the pattern with which behaviors are shared among time series. Via the Indian buffet process representation of the beta process predictive distributions, we develop an exact Markov chain Monte Carlo inference method. In particular, our approach uses the sum-product algorithm to efficiently compute Metropolis-Hastings acceptance probabilities, and explores new dynamical behaviors via birth/death proposals. We validate our sampling algorithm using several synthetic datasets, and also demonstrate promising unsupervised segmentation of visual motion capture data.

Non-parametric Bayesian techniques are considered for learning dictionaries for sparse image representations, with applications in denoising, inpainting and compressive sensing (CS). The beta process is employed as a prior for learning the dictionary, and this non-parametric method naturally infers an appropriate dictionary size. The Dirichlet process and a probit stick-breaking process are also considered to exploit structure within an image. The proposed method can learn a sparse dictionary in situ; training images may be exploited if available, but they are not required. Further, the noise variance need not be known, and can be non-stationary. Another virtue of the proposed method is that sequential inference can be readily employed, thereby allowing scaling to large images. Several example results are presented, using both Gibbs and variational Bayesian inference, with comparisons to other state-of-the-art approaches.

Continuously-Adaptive Discretization for Message-Passing (CAD-MP) is a new message-passing algorithm employing adaptive discretization. Most previous message-passing algorithms approximated arbitrary continuous probability distributions using either: a family of continuous distributions such as the exponential family; a particle-set of discrete samples; or a fixed, uniform discretization. In contrast, CAD-MP uses a discretization that is (i) non-uniform, and (ii) adaptive. The non-uniformity allows CAD-MP to localize interesting features (such as sharp peaks) in the marginal belief distributions with time complexity that scales logarithmically with precision, as opposed to uniform discretization which scales at best linearly. We give a principled method for altering the non-uniform discretization according to information-based measures. CAD-MP is shown in experiments on simulated data to estimate marginal beliefs much more precisely than competing approaches for the same computational expense.

We show that an important and computationally challenging solution space feature of the graph coloring problem (COL), namely the number of clusters of solutions, can be accurately estimated by a technique very similar to one for counting the number of solutions. This cluster counting approach can be naturally written in terms of a new factor graph derived from the factor graph representing the COL instance. Using a variant of the Belief Propagation inference framework, we can efficiently approximate cluster counts in random COL problems over a large range of graph densities. We illustrate the algorithm on instances with up to 100, 000 vertices. Moreover, we supply a methodology for computing the number of clusters exactlyusing advanced techniques from the knowledge compilation literature.