Training a structured prediction model involves performing several loss-augmented inference steps. Over the lifetime of the training, many of these inference problems, although different, share the same solution. We propose AI-DCD, an Amortized Inference framework for Dual Coordinate Descent method, an approximate learning algorithm, that accelerates the training process by exploiting this redundancy of solutions, without compromising the performance of the model. We show the efficacy of our method by training a structured SVM using dual coordinate descent for an entityrelation extraction task. Our method learns the same model as an exact training algorithm would, but call the inference engine only in 10% – 24% of the inference problems encountered during training. We observe similar gains on a multi-label classification task and with a Structured Perceptron model for the entity-relation task.

This paper presents a large-scale sparse coding algorithm to deal with the challenging problem of noise-robust semi-supervised learning over very large data with only few noisy initial labels. By giving an L1-norm formulation of Laplacian regularization directly based upon the manifold structure of the data, we transform noise-robust semi-supervised learning into a generalized sparse coding problem so that noise reduction can be imposed upon the noisy initial labels. Furthermore, to keep the scalability of noise-robust semi-supervised learning over very large data, we make use of both nonlinear approximation and dimension reduction techniques to solve this generalized sparse coding problem in linear time and space complexity. Finally, we evaluate the proposed algorithm in the challenging task of large-scale semi-supervised image classification with only few noisy initial labels. The experimental results on several benchmark image datasets show the promising performance of the proposed algorithm.

AI planning techniques often require a given set of action models provided as input. Creating action models is, however, a difficult task that costs much manual effort. The problem of action-model acquisition has drawn a lot of interest from researchers in the past. Despite the success of the previous systems, they are all based on the assumption that there are enough training examples for learning high-quality action models. In many real-world applications, e.g., military operation, collecting a large amount of training examples is often both difficult and costly. Instead of collecting training examples, we assume there are abundant annotators, i.e., the crowd, available to provide information learning action models. Specifically, we first build a set of soft constraints based on the labels (true or false) given by the crowd or annotators. We then builds a set of soft constraints based on the input plan traces. After that we put all the constraints together and solve them using a weighted MAX-SAT solver, and convert the solution of the solver to action models. We finally exhibit that our approach is effective in the experiment.

Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. We formulate greedy policy learning in the Easy-first approach as a novel non-convex optimization problem and solve it via an efficient Majorization Minimizatoin (MM) algorithm. Results on within-document coreference and cross-document joint entity and event coreference tasks demonstrate that the proposed approach achieves statistically significant performance improvement over existing training regimes for Easy-first and is less susceptible to overfitting.

Advice giving has been long explored in artificial intelligence to build robust learning algorithms. We consider advice giving in relational domains where the noise is systematic. The advice is provided as logical statements that are then explicitly considered by the learning algorithm at every update. Our empirical evidence proves that human advice can effectively accelerate learning in noisy structured domains where so far humans have been merely used as labelers or as designers of initial structure of the model.

While most work on trajectory mining is applied to pre- dict movements of mobile users, in this paper we consider a more general problem of building behavior models of users from their state-action trajectories. We assume that the user behavior can be compactly modeled as a Probabilistic State-Dependent Grammar (PSDG) which represents a hierarchical policy. The key problem is that while the states and actions of the user are directly observed, his intentional structure is not. We propose to learn the user’s policy from a set of selected trajectories and intention queries at selected states in the trajectory. Our main contributions are an algorithm for learning hierarchical policies from state-action trajectories, and principled heuristics for selecting suitable trajectories and intention queries. Experiments in multiple domains show that our approach is effective and more sample-efficient than learning non-hierarchical policies.

A fundamental challenge in calcium imaging has been to infer the timing of action potentials from the measured noisy calcium fluorescence traces. We systematically evaluate a range of spike inference algorithms on a large benchmark dataset recorded from varying neural tissue (V1 and retina) using different calcium indicators (OGB-1 and GCamp6). We show that a new algorithm based on supervised learning in flexible probabilistic models outperforms all previously published techniques, setting a new standard for spike inference from calcium signals. Importantly, it performs better than other algorithms even on datasets not seen during training. Future data acquired in new experimental conditions can easily be used to further improve its spike prediction accuracy and generalization performance. Finally, we show that comparing algorithms on artificial data is not informative about performance on real population imaging data, suggesting that a benchmark dataset may greatly facilitate future algorithmic developments.

In (\cite{zhang2014nonlinear,zhang2014nonlinear2}), we have viewed machine learning as a coding and dimensionality reduction problem, and further proposed a simple unsupervised dimensionality reduction method, entitled deep distributed random samplings (DDRS). In this paper, we further extend it to supervised learning incrementally. The key idea here is to incorporate label information into the coding process by reformulating that each center in DDRS has multiple output units indicating which class the center belongs to. The supervised learning method seems somewhat similar with random forests (\cite{breiman2001random}), here we emphasize their differences as follows. (i) Each layer of our method considers the relationship between part of the data points in training data with all training data points, while random forests focus on building each decision tree on only part of training data points independently. (ii) Our method builds gradually-narrowed network by sampling less and less data points, while random forests builds gradually-narrowed network by merging subclasses. (iii) Our method is trained more straightforward from bottom layer to top layer, while random forests build each tree from top layer to bottom layer by splitting. (iv) Our method encodes output targets implicitly in sparse codes, while random forests encode output targets by remembering the class attributes of the activated nodes. Therefore, our method is a simpler, more straightforward, and maybe a better alternative choice, though both methods use two very basic elements---randomization and nearest neighbor optimization---as the core. This preprint is used to protect the incremental idea from (\cite{zhang2014nonlinear,zhang2014nonlinear2}). Full empirical evaluation will be announced carefully later.

We learn (memorize) multiplication tables, learn (discover how) to walk, learn (build UP an understanding of, then an ability to synthesize) languages. Many subtasks and capabilities are involved in these various kinds of learning. One capability central to many kinds of learning is the ability to generalize: to take into account a large number of specific observations, then to extract and retain the important common features that characterize classes of these observations. This generalization problem has received considerable attention for two decades in the fields of Artificial Intelligence, Psychology, and Pattern Recognition (e.g., [Bruner, 1956],

INTRODUCTION Further progress in the application of computers to many practical fields seems to depend heavily on the success in implementing learning and inductive processes within machines. For example, to develop a consultation system for medical or plant disease diagnosis, prognosis and decision making in general, it is very desirable, perhaps even necessary, to be able to'teach' the system through examples of correct and/or incorrect decisions, rather than by precisely describing the decision process in its full generality and then transforming this description into a computer program. A similar situation exists in computer chess. The development of computer programs playing at the master level (especially the end games) seems to be a formidable task if the programs are not eventually able to learn and improve on their decision making rules through the specific examples of games, rather than by being explicitly told all the rules. Due to easy access to human knowledge about chess and the relative simplicity of testing the results, chess is one of the most attractive testing domains for inductive inference programs. This report presents first results from an experiment on the application of an inductive learning program called AQVAL/1 developed at the University of Illinois, to chess end games.