Agents that can learn new tasks through interactive instruction can utilize goal information to search for and learn flexible policies. This approach can be resilient to variations in initial conditions or issues that arise during execution. However, if a task is not easily formulated as achieving a goal or if the agent lacks sufficient domain knowledge for planning, other methods are required. We present a hybrid approach to interactive task learning that can learn both goal-oriented and procedural tasks, and mixtures of the two, from human natural language instruction. We describe this approach, go through two examples of learning tasks, and outline the space of tasks that the system can learn. We show that our approach can learn a variety of goal-oriented and procedural tasks from a single example and is robust to different amounts of domain knowledge.

Multi-label classification is crucial to several practical applications including document categorization, video tagging, targeted advertising etc. Training a multi-label classifier requires a large amount of labeled data which is often unavailable or scarce. Labeled data is then acquired by consulting multiple labelers---both human and machine. Inspired by ensemble methods, our premise is that labels inferred with high consensus among labelers, might be closer to the ground truth. We propose strategies based on interaction and active learning to obtain higher quality labels that potentially lead to greater consensus. We propose a novel formulation that aims to collectively optimize the cost of labeling, labeler reliability, label-label correlation and inter-labeler consensus. Evaluation on data labeled by multiple labelers (both human and machine) shows that our consensus output is closer to the ground truth when compared to the "majority" baseline. We present illustrative cases where it even improves over the existing ground truth. We also present active learning strategies to leverage our consensus model in interactive learning settings. Experiments on several real-world datasets (publicly available) demonstrate the efficacy of our approach in achieving promising classification results with fewer labeled data.

It is well-known that the Gale-Shapley algorithm is not truthful for all agents. Previous studies in this category concentrate on manipulations using incomplete preference lists by a single woman and by the set of all women. Little is known about manipulations by a subset of women. In this paper, we consider manipulations by any subset of women with arbitrary preferences. We show that a strong Nash equilibrium of the induced manipulation game always exists among the manipulators and the equilibrium outcome is unique and Pareto-dominant. In addition, the set of matchings achievable by manipulations has a lattice structure. We also examine the super-strong Nash equilibrium in the end.

Peer grading, allowing students/peers to evaluate others' assignments, offers a promising solution for scaling evaluation and learning to large-scale educational systems. A key challenge in peer grading is motivating peers to grade diligently. While existing spot-checking (SC) mechanisms can prevent peer collusion where peers coordinate to report the uninformative grade, they unrealistically assume that peers have the same grading reliability and cost. This paper studies the general Optimal Spot-Checking (OptSC) problem of determining the probability each assignment needs to be checked to maximize assignments' evaluation accuracy aggregated from peers, and takes into consideration 1) peers' heterogeneous characteristics, and 2) peers' strategic grading behaviors to maximize their own utility. We prove that the bilevel OptSC is NP-hard to solve. By exploiting peers' grading behaviors, we first formulate a single level relaxation to approximate OptSC. By further exploiting structural properties of the relaxed problem, we propose an efficient algorithm to that relaxation, which also gives a good approximation of the original OptSC. Extensive experiments on both synthetic and real datasets show significant advantages of the proposed algorithm over existing approaches.

The learning problem for Factorial Hidden Markov Models with discrete and multi-variate latent variables remains a challenge. Inference of the latent variables required for the E-step of Expectation Minimization algorithms is usually computationally intractable. In this paper we propose a variational learning algorithm mimicking the Baum-Welch algorithm. By approximating the filtering distribution with a variational distribution parameterized by a recurrent neural network, the computational complexity of the learning problem as a function of the number of hidden states can be reduced to quasilinear instead of quadratic time as required by traditional algorithms such as Baum-Welch whilst making minimal independence assumptions. We evaluate the performance of the resulting algorithm, which we call Variational BOLT, in the context of unsupervised end-to-end energy disaggregation. We conduct experiments on the publicly available REDD dataset and show competitive results when compared with a supervised inference approach and state-of-the-art results in an unsupervised setting.

Recently proposed models which learn to write computer programs from data use either input/output examples or rich execution traces. Instead, we argue that a novel alternative is to use a glass-box scoring function, given as a program itself that can be directly inspected. Glass-box optimization covers a wide range of problems, from computing the greatest common divisor of two integers, to learning-to-learn problems. In this paper, we present an intelligent search system which learns, given the partial program and the glass-box problem, the probabilities over the space of programs. We empirically demonstrate that our informed search procedure leads to significant improvements compared to brute-force program search, both in terms of accuracy and time. For our experiments we use rich context free grammars inspired by number theory, text processing, and algebra. Our results show that (i) running our framework iteratively can considerably increase the number of problems solved, (ii) our framework can improve itself even in domain agnostic scenarios, and (iii) it can solve problems that would be otherwise too slow to solve with brute-force search.

The Leiter International Performance Scale-Revised (Leiter-R) is a standardized cognitive test that seeks to "provide a nonverbal measure of general intelligence by sampling a wide variety of functions from memory to nonverbal reasoning." Understanding the computational building blocks of nonverbal cognition, as measured by the Leiter-R, is an important step towards understanding human nonverbal cognition, especially with respect to typical and atypical trajectories of child development. One subtest of the Leiter-R, Form Completion, involves synthesizing and localizing a visual figure from its constituent slices. Form Completion poses an interesting nonverbal problem that seems to combine several aspects of visual memory, mental rotation, and visual search. We describe a new computational cognitive model that addresses Form Completion using a novel, mental-rotation-friendly image representation that we call the Polar Augmented Resolution (PolAR) Picture, which enables high-fidelity mental rotation operations. We present preliminary results using actual Leiter-R test items and discuss directions for future work.

Document-based Question Answering (DBQA) in Natural Language Processing (NLP) is important but difficult because of the long document and the complex question. Most of previous deep learning methods mainly focus on the similarity computation between two sentences. However, DBQA stems from the reading comprehension in some degree, which is originally used to train and test people's ability of reading and logical thinking. Inspired by the strategy of doing reading comprehension tests, we propose a unified model based on the human-like reading strategy. The unified model contains three major encoding layers that are consistent to different steps of the reading strategy, including the basic encoder, combined encoder and hierarchical encoder. We conduct extensive experiments on both the English WikiQA dataset and the Chinese dataset, and the experimental results show that our unified model is effective and yields state-of-the-art results on WikiQA dataset.

The brain uses spikes in neural circuits to perform many dynamical computations. The computations are performed with properties such as spiking efficiency, i.e. minimal number of spikes, and robustness to noise. A major obstacle for learning computations in artificial spiking neural networks with such desired biological properties is due to lack of our understanding of how biological spiking neural networks learn computations. Here, we consider the credit assignment problem, i.e. determining the local contribution of each synapse to the network's global output error, for learning nonlinear dynamical computations in a spiking network with the desired properties of biological networks. We approach this problem by fusing the theory of efficient, balanced neural networks (EBN) with nonlinear adaptive control theory to propose a local learning rule. Locality of learning rules are ensured by feeding back into the network its own error, resulting in a learning rule depending solely on presynaptic inputs and error feedbacks. The spiking efficiency and robustness of the network are guaranteed by maintaining a tight excitatory/inhibitory balance, ensuring that each spike represents a local projection of the global output error and minimizes a loss function. The resulting networks can learn to implement complex dynamics with very small numbers of neurons and spikes, exhibit the same spike train variability as observed experimentally, and are extremely robust to noise and neuronal loss.

Badges are a common, and sometimes the only, method of incentivizing users to perform certain actions on on- line sites. However, due to many competing factors influencing user temporal dynamics, it is difficult to determine whether the badge had (or will have) the intended effect or not. In this paper, we introduce two complementary approaches for determining badge influence on users. In the first one, we cluster users’ temporal traces (represented with Poisson processes) and apply covariates (user features) to regularize results. In the second approach, we first classify users’ temporal traces with a novel statistical framework, and then we refine the classification results with a semi-supervised clustering of covariates. Outcomes obtained from an evaluation on synthetic datasets and experiments on two badges from a pop- ular Q&A platform confirm that it is possible to validate, characterize and to some extent predict users affected by the badge.