Total: 90
Applications that require heterogeneous sensor deployments continue to face practical challenges owing to resource constraints within their operating environments (i.e. energy efficiency, computational power and reliability). This has motivated the need for effective ways of selecting a sensing strategy that maximizes detection accuracy for events of interest using available resources and data-driven approaches. Inspired by those limitations, we ask a fundamental question: whether state-of-the-art Recurrent Neural Networks can observe different series of data and communicate their hidden states to collectively solve an objective in a distributed fashion. We realize our answer by conducting a series of systematic analyses of a Communicating Recurrent Neural Network architecture on varying time-steps, objective functions and number of nodes. The experimental setup we employ models tasks synonymous with those in Wireless Sensor Networks. Our contributions show that Recurrent Neural Networks can communicate through their hidden states and we achieve promising results.
The proliferation of Android apps has resulted in many malicious apps entering the market and causing significant damage. Robust techniques that determine if an app is malicious are greatly needed. We propose the use of a network-based approach to effectively separate malicious from benign apps, based on a small labeled dataset. The apps in our dataset come from the Google Play Store and have been scanned for malicious behavior using Virus Total to produce a ground truth dataset with labels malicous or benign. The apps in the resulting dataset have been represented using binary feature vectors (where the features represent permissions, intent actions, discriminative APIs, obfuscation signatures, and native code signatures). We have used the feature vectors corresponding to apps to build a weighted network that captures the “closeness” between apps. We propagate labels from the labeled apps to unlabeled apps, and evaluate the effectiveness of the proposed approach using the F1-measure. We have conducted experiments to compare three variants of the label propagation approaches on datasets that include increasingly larger amounts of labeled data. The results have shown that a variant proposed in this study gives the best results overall.
Learning flexible latent representation of observed data is an important precursor for most downstream AI applications. To this end, we propose a novel form of variational encoder, i.e., encapsulated variational encoders (EVE) to exert direct control over encoded latent representations along with its learning algorithm, i.e., the EVE compatible automatic variational differentiation inference algorithm. Armed with this property, our derived EVE is capable of learning converged and diverged latent representations. Using CIFAR-10 as an example, we show that the learning of converged latent representations brings a considerable improvement on the discriminative performance of the semi-supervised EVE. Using MNIST as a demonstration, the generative modelling performance of the EVE induced variational auto-encoder (EVAE) can be largely enhanced with the help of learned diverged latent representations.
In our research, we study the problem of learning a sequence of supervised tasks. This is a long-standing challenge in machine learning. Our work relies on transfer of knowledge between hypotheses learned with Support Vector Machines. Transfer occurs in two directions: forward and backward. We have proposed to selectively transfer forward support vector coefficients from previous hypotheses as upper-bounds on support vector coefficients to be learned on a target task. We also proposed a novel method for refining existing hypotheses by transferring backward knowledge from a target hypothesis learned recently. We have improved this method through a hypothesis refinement approach that refines whilst encouraging retention of knowledge. Our contribution is represented in a long-term learning framework for binary classification tasks received sequentially one at a time.
We introduce a new manipulation strategy available to women in the men-proposing stable matching, called manipulation through an accomplice. In this strategy, a woman can team up with a potential male “accomplice” who manipulates on her behalf to obtain a better match for her. We investigate the stability of the matching obtained after this manipulation, provide an algorithm to compute such strategies, and show its benefit compared to single-woman manipulation strategies.
Developing human-machine trust is a prerequisite for adoption of machine learning systems in decision critical settings (e.g healthcare and governance). Users develop appropriate trust in these systems when they understand how the systems make their decisions. Interpretability not only helps users understand what a system learns but also helps users contest that system to align with their intuition. We propose an algorithm, AVA: Aggregate Valuation of Antecedents, that generates a consensus feature attribution, retrieving local explanations and capturing global patterns learned by a model. Our empirical results show that AVA rivals current benchmarks.
We consider the problem of allocating a set of indivisible goods among a group of homogeneous agents under matroid constraints and additive valuations, in a fair manner. We propose a novel algorithm that computes a fair allocation for instances with additive and identical valuations, even under matroid constraints. Our result provides a computational anchor to the existential result of the fairness notion, called EF1 (envy-free up to one good) by Biswas and Barman in this setting. We further provide examples to show that the fairness notions stronger than EF1 does not always exist in this setting.
Optimal Coalition Structure Generation (CSG) is a significant research problem that remains difficult to solve. Given n agents, the ODP-IP algorithm (Michalak et al. 2016) achieves the current lowest worst-case time complexity of O(3n). We devise an Imperfect Dynamic Programming (ImDP) algorithm for CSG with runtime O(n2n). Imperfect algorithm means that there are some contrived inputs for which the algorithm fails to give the optimal result. Experimental results confirmed that ImDP algorithm performance is better for several data distribution, and for some it improves dramatically ODP-IP. For example, given 27 agents, with ImDP for agentbased uniform distribution time gain is 91% (i.e. 49 minutes).
A method based on Robust Principle Component Analysis (RPCA) technique is proposed to detect small targets in infrared images. Using the low rank characteristic of background and the sparse characteristic of target, the observed image is regarded as the sum of a low-rank background matrix and a sparse outlier matrix, and then the decomposition is solved by the RPCA. The infrared small target is extracted from the single-frame image or multi-frame sequence. In order to get more efficient algorithm, the iteration process in the augmented Lagrange multiplier method is improved. The simulation results show that the method can detect out the small target precisely and efficiently.
Attention-based recurrent neural network models for joint intent detection and slot filling have achieved a state-of-the-art performance. Most previous works exploited semantic level information to calculate the attention weights. However, few works have taken the importance of word level information into consideration. In this paper, we propose WAIS, word attention for joint intent detection and slot filling. Considering that intent detection and slot filling have a strong relationship, we further propose a fusion gate that integrates the word level information and semantic level information together for jointly training the two tasks. Extensive experiments show that the proposed model has robust superiority over its competitors and sets the state-of-the-art.
For large-scale iris recognition tasks, the determination of classification thresholds remains a challenging task, especially in practical applications where sample space is growing rapidly. Due to the complexity of iris samples, the classification threshold is difficult to determine with the increase of samples. The key issue to solving such threshold determination problems is to obtain iris feature vectors with more obvious discrimination. Therefore, we train deep convolutional neural networks based on a large number of iris samples to extract iris features. More importantly, an optimized center loss function referred to Tight Center (T -Center) Loss is used to solve the problem of insufficient discrimination caused by Softmax loss function. In order to evaluate the effectiveness of our proposed method, we use cosine similarity to estimate the similarity between the features on the published datasets CASIA-IrisV4 and IITD2.0. Our experiment results demonstrate that the T -Center loss can minimize intra-class variance and maximize inter-class variance, which achieve significant performance on the benchmark experiments.
Lacking in sequence preserving mechanism, existing heterogeneous information network (HIN) embedding discards the essential type sequence information during embedding. We propose a Type Sequence Preserving HIN Embedding model (SeqHINE) which expands the HIN embedding to sequence level. SeqHINE incorporates the type sequence information via type-aware GRU and preserves representative sequence information by decay function. Abundant experiments show that SeqHINE can outperform state-of-the-art even with 50% less labeled data.
Facial verification is a core problem studied by researchers in computer vision. Recently published one-to-one comparison models have successfully achieved accuracy results that surpass the abilities of humans. A natural extension to the one-to-one facial verification problem is a one-to-many classification. In this abstract, we present our exploration of different methods of performing one-to-many facial verification using low-resolution images. The CSEye model introduces a direct comparison between the features extracted from each of the candidate images and the suspect before performing the classification task. Initial experiments using 10-to-1 comparisons of faces from the Labelled Faces of the Wild dataset yield promising results.
In this paper, we propose a Multi-Task learning approach for Answer Selection (MTAS), motivated by the fact that humans have no difficulty performing such task because they possess capabilities of multiple domains (tasks). Specifically, MTAS consists of two key components: (i) A category classification model that learns rich category-aware document representation; (ii) An answer selection model that provides the matching scores of question-answer pairs. These two tasks work on a shared document encoding layer, and they cooperate to learn a high-quality answer selection system. In addition, a multi-head attention mechanism is proposed to learn important information from different representation subspaces at different positions. We manually annotate the first Chinese question answering dataset in law domain (denoted as LawQA) to evaluate the effectiveness of our model. The experimental results show that our model MTAS consistently outperforms the compared methods.1
Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples available in the target task), meta-learning approaches that optimize for future task learning have outperformed the typical transfer approach of initializing model weights from a pretrained starting point. But as we experimentally show, metalearning algorithms that work well in the few-class setting do not generalize well in many-shot and many-class cases. In this paper, we propose a joint training approach that combines both transfer-learning and meta-learning. Benefiting from the advantages of each, our method obtains improved generalization performance on unseen target tasks in both few- and many-class and few- and many-shot scenarios.
In several reinforcement learning (RL) scenarios, mainly in security settings, there may be adversaries trying to interfere with the reward generating process. However, when non-stationary environments as such are considered, Q-learning leads to suboptimal results (Busoniu, Babuska, and De Schutter 2010). Previous game-theoretical approaches to this problem have focused on modeling the whole multi-agent system as a game. Instead, we shall face the problem of prescribing decisions to a single agent (the supported decision maker, DM) against a potential threat model (the adversary). We augment the MDP to account for this threat, introducing Threatened Markov Decision Processes (TMDPs). Furthermore, we propose a level-k thinking scheme resulting in a new learning framework to deal with TMDPs. We empirically test our framework, showing the benefits of opponent modeling.
Intelligent Tutoring Systems (ITS) have great potential to change the educational landscape by bringing scientifically tested one-to-one tutoring to remote and under-served areas. However, effective ITSs are too complex to perfect. Instead, a practical guiding principle for ITS development and improvement is to fix what’s most broken. In this paper we present SPOT (Statistical Probe of Tutoring): a tool that mines data logged by an Intelligent Tutoring System to identify the ‘hot spots’ most detrimental to its efficiency and effectiveness in terms of its software reliability, usability, task difficulty, student engagement, and other criteria. SPOT uses heuristics and machine learning to discover, characterize, and prioritize such hot spots in order to focus ITS refinement on what matters most. We applied SPOT to data logged by RoboTutor, an ITS that teaches children basic reading, writing and arithmetic.
Word Sense Disambiguation (WSD), as a tough task in Natural Language Processing (NLP), aims to identify the correct sense of an ambiguous word in a given context. There are two mainstreams in WSD. Supervised methods mainly utilize labeled context to train a classifier which generates the right probability distribution of word senses. Meanwhile knowledge-based (unsupervised) methods which focus on glosses (word sense definitions) always calculate the similarity of context-gloss pair as score to find out the right word sense. In this paper, we propose a generative adversarial framework WSD-GAN which combines two mainstream methods in WSD. The generative model, based on supervised methods, tries to generate a probability distribution over the word senses. Meanwhile the discriminative model, based on knowledge-based methods, focuses on predicting the relevancy of the context-gloss pairs and identifies the correct pairs over the others. Furthermore, in order to optimize both two models, we leverage policy gradient to enhance the performances of the two models mutually. Our experimental results show that WSD-GAN achieves competitive results on several English all-words WSD datasets.
In this paper, we define a new problem of multi-layer network community detection, namely higher-order multi-layer community detection. A multi-layer motif (M-Motif) approach is proposed, which discovers communities with good intralayer higher-order community quality while preserving interlayer higher-order community consistency. Experimental results have confirmed the superiority of the proposed method.
Visual surveillance through closed circuit television (CCTV) can help to prevent crime. In this paper, we propose an automatic visual surveillance network (AVS-Net), which simultaneously performs image processing and object detection to determine the dangers of situations captured by CCTV. In addition, we add a relation module to infer the relationships of the objects in the images. Experimental results show that the relation module greatly improves classification accuracy, even if there is not enough information.
In automated material handling systems (AMHS), delivery time is an important issue directly associated with the production cost and the quality of the product. In this paper, we propose a dynamic routing strategy to shorten delivery time and delay. We set the target of control by analyzing traffic flows and selecting the region with the highest flow rate and congestion frequency. Then, we impose a routing cost in order to dynamically reflect the real-time changes of traffic states. Our deep reinforcement learning model consists of a Q-learning step and a recurrent neural network, through which traffic states and action values are predicted. Experiment results show that the proposed method decreases manufacturing costs while increasing productivity. Additionally, we find evidence the reinforcement learning structure proposed in this study can autonomously and dynamically adjust to the changes in traffic patterns.
In multilingual societies like the Indian subcontinent, use of code-switched languages is much popular and convenient for the users. In this paper, we study offense and abuse detection in the code-switched pair of Hindi and English (i.e, Hinglish), the pair that is the most spoken. The task is made difficult due to non-fixed grammar, vocabulary, semantics and spellings of Hinglish language. We apply transfer learning and make a LSTM based model for hate speech classification. This model surpasses the performance shown by the current best models to establish itself as the state-of-the-art in the unexplored domain of Hinglish offensive text classification. We also release our model and the embeddings trained for research purposes.
This work explores the design of a central collaborative driving strategy between connected cars with the objective of improving road safety in case of highway on-ramp merging scenario. Based on a suitable method for predicting vehicle motion and behavior for a central collaborative strategy, a dynamic Bayesian network method that predicts the intention of drivers in highway on-ramp is proposed. The method was validated using real data of detailed vehicle trajectories on a segment of interstate 80 in Emeryville, California.
Learning temporal abstractions which are partial solutions to a task and could be reused for solving other tasks is an ingredient that can help agents to plan and learn efficiently. In this work, we tackle this problem in the options framework. We aim to autonomously learn options which are specialized in different state space regions by proposing a notion of interest functions, which generalizes initiation sets from the options framework for function approximation. We build on the option-critic framework to derive policy gradient theorems for interest functions, leading to a new interest-option-critic architecture.
Previously proposed variational techniques for approximate MMAP inference in complex graphical models of high-order factors relax a dual variational objective function to obtain its tractable approximation, and further perform MMAP inference in the resulting simplified graphical model, where the sub-graph with decision variables is assumed to be a disconnected forest. In contrast, we developed novel variational MMAP inference algorithms and proximal convergent solvers, where we can improve the approximation accuracy while better preserving the original MMAP query by designing such a dual variational objective function that an upper bound approximation is applied only to the entropy of decision variables. We evaluate the proposed algorithms on both simulated synthetic datasets and diagnostic Bayesian networks taken from the UAI inference challenge, and our solvers outperform other variational algorithms in a majority of reported cases. Additionally, we demonstrate the important real-life application of the proposed variational approaches to solve complex tasks of policy optimization by MMAP inference, and performance of the implemented approximation algorithms is compared. Here, we demonstrate that the original task of optimizing POMDP controllers can be approached by its reformulation as the equivalent problem of marginal-MAP inference in a novel single-DBN generative model, which guarantees that the control policies computed by probabilistic inference over this model are optimal in the traditional sense. Our motivation for approaching the planning problem through probabilistic inference in graphical models is explained by the fact that by transforming a Markovian planning problem into the task of probabilistic inference (a marginal MAP problem) and applying belief propagation techniques in generative models, we can achieve a computational complexity reduction from PSPACE-complete or NEXP-complete to NPPP-complete in comparison to solving the POMDP and Dec-POMDP models respectively search vs. dynamic programming).