We study the problem of reducing test-time acquisition costs in classification systems. Our goal is to learn decision rules that adaptively select sensors for each example as necessary to make a confident prediction. We model our system as a directed acyclic graph (DAG) where internal nodes correspond to sensor subsets and decision functions at each node choose whether to acquire a new sensor or classify using the available measurements. This problem can be naturally posed as an empirical risk minimization over training data. Rather than jointly optimizing such a highly coupled and non-convex problem over all decision nodes, we propose an efficient algorithm motivated by dynamic programming. We learn node policies in the DAG by reducing the global objective to a series of cost sensitive learning problems. Our approach is computationally efficient and has proven guarantees of convergence to the optimal system for a fixed architecture. In addition, we present an extension to map other budgeted learning problems with large number of sensors to our DAG architecture and demonstrate empirical performance exceeding state-of-the-art algorithms for data composed of both few and many sensors.

Solving real world problems with embedded neural networks requires both training algorithms that achieve high performance and compatible hardware that runs in real time while remaining energy efficient. For the former, deep learning using backpropagation has recently achieved a string of successes across many domains and datasets. For the latter, neuromorphic chips that run spiking neural networks have recently achieved unprecedented energy efficiency. To bring these two advances together, we must first resolve the incompatibility between backpropagation, which uses continuous-output neurons and synaptic weights, and neuromorphic designs, which employ spiking neurons and discrete synapses. Our approach is to treat spikes and discrete synapses as continuous probabilities, which allows training the network using standard backpropagation. The trained network naturally maps to neuromorphic hardware by sampling the probabilities to create one or more networks, which are merged using ensemble averaging. To demonstrate, we trained a sparsely connected network that runs on the TrueNorth chip using the MNIST dataset. With a high performance network (ensemble of $64$), we achieve $99.42\%$ accuracy at $121 \mu$J per image, and with a high efficiency network (ensemble of $1$) we achieve $92.7\%$ accuracy at $0.408 \mu$J per image.

Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these benefits while avoiding potential pitfalls. This article gives numerous examples (which should by no means be construed as an exhaustive list) of such worthwhile research aimed at ensuring that AI remains robust and beneficial.

Recent advances in cognitive computing componentry combined with other factors are leading to commercially viable cognitive systems. From chips to smart phones to public and private clouds, industrial strength “cognition as a service” is beginning to appear at all scales in business and society. Furthermore, in the age of zettabytes on the way to yottabytes, the designers, engineers, and managers of future smart systems will depend on cognition as a service. Cognition as a service can help unlock the mysteries of big data and ultimately boost the creativity and productivity of professionals and their teams, the productive output of industries and organizations, as well as the GDP (gross domestic product) of regions and nations. In this and the next decade, cognition as a service will allow us to re-image work practices, augmenting and scaling expertise to transform professions, industries, and regions.

Active problem solving has been shown to be one of the most effective ways to acquire complex skills. Whether one is learning a programming language by implementing a computer program, or learning calculus by solving problems, context sensitive feedback and guidance are crucial to keeping problem solving efforts fruitful and efficient. This article reviews AI-based algorithms that can diagnose student difficulties during active problem solving and serve as the basis for providing context-sensitive and individualized guidance. The article also describes the crucial role sensor based estimates of cognitive resources such as working memory capacity and attention can play in enhancing the diagnostic capabilities of intelligent instructional systems.

Human-centered design of wearable robots involves the development of innovative science and technologies that minimize the mismatch between humans’ and machines’ capabilities, leading to their intuitive integration and confluent interaction. Here, we summarize our human-centered approach to the design of closed-loop brain-machine interfaces (BMI) to powered prostheses and exoskeletons that allow people to act beyond their impaired or diminished physical or sensory-motor capabilities. The goal is to develop multifunctional human-machine interfaces with integrated diagnostic, assistive and therapeutic functions. Moreover, these complex human-machine systems should be effective, reliable, safe and engaging and support the patient in performing intended actions with minimal effort and errors with adequate interaction time. To illustrate our approach, we review an example of a user-in-the-loop, patient-centered, non-invasive BMI system to a powered exoskeleton for persons with paraplegia. We conclude with a summary of challenges to the translation of these complex human-machine systems to the end-user.

This introduction focuses on how human-centered computing (HCC) is changing the way that people think about information technology. The AI perspective views this HCC framework as embodying a systems view, in which human thought and action are linked and equally important in terms of analysis, design, and evaluation. This emerging technology provides a new research outlook for AI applications, with new research goals and agendas.

We consider the following multi-component sparse PCA problem:given a set of data points, we seek to extract a small number of sparse components with \emph{disjoint} supports that jointly capture the maximum possible variance.Such components can be computed one by one, repeatedly solving the single-component problem and deflating the input data matrix, but this greedy procedure is suboptimal.We present a novel algorithm for sparse PCA that jointly optimizes multiple disjoint components. The extracted features capture variance that lies within a multiplicative factor arbitrarily close to $1$ from the optimal.Our algorithm is combinatorial and computes the desired components by solving multiple instances of the bipartite maximum weight matching problem.Its complexity grows as a low order polynomial in the ambient dimension of the input data, but exponentially in its rank.However, it can be effectively applied on a low-dimensional sketch of the input data.We evaluate our algorithm on real datasets and empirically demonstrate that in many cases it outperforms existing, deflation-based approaches.

Linear regression studies the problem of estimating a model parameter $\beta^* \in \R^p$, from $n$ observations $\{(y_i,x_i)\}_{i=1}^n$ from linear model $y_i = \langle \x_i,\beta^* \rangle + \epsilon_i$. We consider a significant generalization in which the relationship between $\langle x_i,\beta^* \rangle$ and $y_i$ is noisy, quantized to a single bit, potentially nonlinear, noninvertible, as well as unknown. This model is known as the single-index model in statistics, and, among other things, it represents a significant generalization of one-bit compressed sensing. We propose a novel spectral-based estimation procedure and show that we can recover $\beta^*$ in settings (i.e., classes of link function $f$) where previous algorithms fail. In general, our algorithm requires only very mild restrictions on the (unknown) functional relationship between $y_i$ and $\langle x_i,\beta^* \rangle$. We also consider the high dimensional setting where $\beta^*$ is sparse, and introduce a two-stage nonconvex framework that addresses estimation challenges in high dimensional regimes where $p \gg n$. For a broad class of link functions between $\langle x_i,\beta^* \rangle$ and $y_i$, we establish minimax lower bounds that demonstrate the optimality of our estimators in both the classical and high dimensional regimes.

Deep dynamic generative models are developed to learn sequential dependencies in time-series data. The multi-layered model is designed by constructing a hierarchy of temporal sigmoid belief networks (TSBNs), defined as a sequential stack of sigmoid belief networks (SBNs). Each SBN has a contextual hidden state, inherited from the previous SBNs in the sequence, and is used to regulate its hidden bias. Scalable learning and inference algorithms are derived by introducing a recognition model that yields fast sampling from the variational posterior. This recognition model is trained jointly with the generative model, by maximizing its variational lower bound on the log-likelihood. Experimental results on bouncing balls, polyphonic music, motion capture, and text streams show that the proposed approach achieves state-of-the-art predictive performance, and has the capacity to synthesize various sequences.