A computer vision model operating on an embedded device may need to perform real-time inference; a translation model operating on a cell phone may wish to bound its average compute time in order to be power-efficient. In these cases, there is often a tension between satisfying the constraint and achieving acceptable model performance. These constraints need not be restricted to speed and accuracy, but can reflect preferences for model simplicity or other desiderata. One way to deal with constraints is to build them into models explicitly at training time. This has two major disadvantages: First, it requires manually designing and retraining a new model for each use case.

We analyze the problem of learning a single user's preferences in an active learning setting, sequentially and adaptively querying the user over a finite time horizon. Learning is conducted via choice-based queries, where the user selects her preferred option among a small subset of offered alternatives. These queries have been shown to be a robust and efficient way to learn an individual's preferences. We take a parametric approach and model the user's preferences through a linear classifier, using a Bayesian prior to encode our current knowledge of this classifier. The rate at which we learn depends on the alternatives offered at every time epoch. Under certain noise assumptions, we show that the Bayes-optimal policy for maximally reducing entropy of the posterior distribution of this linear classifier is a greedy policy, and that this policy achieves a linear lower bound when alternatives can be constructed from the continuum. Further, we analyze a different metric called misclassification error, proving that the performance of the optimal policy that minimizes misclassification error is bounded below by a linear function of differential entropy. Lastly, we numerically compare the greedy entropy reduction policy with a knowledge gradient policy under a number of scenarios, examining their performance under both differential entropy and misclassification error.

We build a collaborative filtering recommender system to restore images with impulse noise for which the noisy pixels have been previously identified. We define this recommender system in terms of a new color image representation using three matrices that depend on the noise-free pixels of the image to restore, and two parameters: $k$, the number of features; and $\lambda$, the regularization factor. We perform experiments on a well known image database to test our algorithm and we provide image quality statistics for the results obtained. We discuss the roles of bias and variance in the performance of our algorithm as determined by the values of $k$ and $\lambda$, and provide guidance on how to choose the values of these parameters. Finally, we discuss the possibility of using our collaborative filtering recommender system to perform image inpainting and super-resolution.

This paper is concerned with the problem of stochastic control of gene regulatory networks (GRNs) observed indirectly through noisy measurements and with uncertainty in the intervention inputs. The partial observability of the gene states and uncertainty in the intervention process are accounted for by modeling GRNs using the partially-observed Boolean dynamical system (POBDS) signal model with noisy gene expression measurements. Obtaining the optimal infinite-horizon control strategy for this problem is not attainable in general, and we apply reinforcement learning and Gaussian process techniques to find a near-optimal solution. The POBDS is first transformed to a directly-observed Markov Decision Process in a continuous belief space, and the Gaussian process is used for modeling the cost function over the belief and intervention spaces. Reinforcement learning then is used to learn the cost function from the available gene expression data. In addition, we employ sparsification, which enables the control of large partially-observed GRNs. The performance of the resulting algorithm is studied through a comprehensive set of numerical experiments using synthetic gene expression data generated from a melanoma gene regulatory network.

Blind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no more valid in the presence of intra-class variabilities due to illumination conditions, weathering, slight variations of the pure materials, etc... In this paper, we first describe the results of investigations highlighting intra-class variability measured in real images. Considering these results, a new formulation of the linear mixing model is presented leading to two new methods. Unconstrained Pixel-by-pixel NMF (UP-NMF) is a new blind source separation method based on the assumption of a linear mixing model, which can deal with intra-class variability. To overcome UP-NMF limitations an extended method is proposed, named Inertia-constrained Pixel-by-pixel NMF (IP-NMF). For each sensed spectrum, these extended versions of NMF extract a corresponding set of source spectra. A constraint is set to limit the spreading of each source's estimates in IP-NMF. The methods are tested on a semi-synthetic data set built with spectra extracted from a real hyperspectral image and then numerically mixed. We thus demonstrate the interest of our methods for realistic source variabilities. Finally, IP-NMF is tested on a real data set and it is shown to yield better performance than state of the art methods.

Microwave-based breast cancer detection has been proposed as a complementary approach to compensate for some drawbacks of existing breast cancer detection techniques. Among the existing microwave breast cancer detection methods, machine learning-type algorithms have recently become more popular. These focus on detecting the existence of breast tumours rather than performing imaging to identify the exact tumour position. A key step of the machine learning approaches is feature extraction. One of the most widely used feature extraction method is principle component analysis (PCA). However, it can be sensitive to signal misalignment. This paper presents an empirical mode decomposition (EMD)-based feature extraction method, which is more robust to the misalignment. Experimental results involving clinical data sets combined with numerically simulated tumour responses show that combined features from EMD and PCA improve the detection performance with an ensemble selection-based classifier.

Human-robot interaction (HRI) is an emerging field of research with the aim to integrate robots into human social environments. One of the biggest challenges in the development of social robots is to understand human social norms [1]. It is therefore essential for social robots to possess deep models of social cognition, and be able to learn and adapt in accordance with their shared experiences with human partners. Most of the social robots to date are either preprogrammed, or are controlled by teleoperation or semiautonomous teleoperation [2], and do not possess the ability to learn and update themselves. Designing an adaptable and autonomous sociable robot is particularly challenging, as the robot needs to correctly interpret human behaviors as well as respond appropriately to them.

Although deep learning models have proven effective at solving problems in natural language processing, the mechanism by which they come to their conclusions is often unclear. As a result, these models are generally treated as black boxes, yielding no insight of the underlying learned patterns. In this paper we consider Long Short Term Memory networks (LSTMs) and demonstrate a new approach for tracking the importance of a given input to the LSTM for a given output. By identifying consistently important patterns of words, we are able to distill state of the art LSTMs on sentiment analysis and question answering into a set of representative phrases. This representation is then quantitatively validated by using the extracted phrases to construct a simple, rule-based classifier which approximates the output of the LSTM.

Given a knowledge base (KB) rich in facts about common nouns or generics, such as "all trees produce oxygen" or "some animals live in forests", we consider the problem of deriving additional such facts at a high precision. While this problem has received much attention for named entity KBs such as Freebase, little emphasis has been placed on generics despite their importance for capturing general knowledge. Different from named entity KBs, generics KBs involve implicit or explicit quantification, have more complex underlying regularities, are substantially more incomplete, and violate the commonly used locally closed world assumption (LCWA). Consequently, existing completion methods struggle with this new task. We observe that external information, such as relation schemas and entity taxonomies, if used correctly, can be surprisingly powerful in addressing the challenges associated with generics. Using this insight, we propose a simple yet effective knowledge guided tensor factorization approach that achieves state-of-the-art results on two generics KBs for science, doubling their size at 74\%-86\% precision. Further, to address the paucity of facts about rare entities such as oriole (a bird), we present a novel taxonomy guided submodular active learning method to collect additional annotations that are over five times more effective in inferring further new facts than multiple active learning baselines.

Twitter provides an open and rich source of data for studying human behaviour at scale and is widely used in social and network sciences. However, a major criticism of Twitter data is that demographic information is largely absent. Enhancing Twitter data with user ages would advance our ability to study social network structures, information flows and the spread of contagions. Approaches toward age detection of Twitter users typically focus on specific properties of tweets, e.g., linguistic features, which are language dependent. In this paper, we devise a language-independent methodology for determining the age of Twitter users from data that is native to the Twitter ecosystem. The key idea is to use a Bayesian framework to generalise ground-truth age information from a few Twitter users to the entire network based on what/whom they follow.