Computer Science - Artificial Intelligence Publications (50)


Computer Science - Artificial Intelligence Publications

We present a novel extension of Thompson Sampling for stochastic sequential decision problems with graph feedback, even when the graph structure itself is unknown and/or changing. We provide theoretical guarantees on the Bayesian regret of the algorithm, linking its performance to the underlying properties of the graph. Thompson Sampling has the advantage of being applicable without the need to construct complicated upper confidence bounds for different problems. Read More

In this paper, we improve the previously best known regret bound to achieve $\epsilon$-differential privacy in oblivious adversarial bandits from $\mathcal{O}{(T^{2/3}/\epsilon)}$ to $\mathcal{O}{(\sqrt{T} \ln T /\epsilon)}$. This is achieved by combining a Laplace Mechanism with EXP3. We show that though EXP3 is already differentially private, it leaks a linear amount of information in $T$. Read More

Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples. In this work, we establish that reinforcement learning techniques based on Deep Q-Networks (DQNs) are also vulnerable to adversarial input perturbations, and verify the transferability of adversarial examples across different DQN models. Furthermore, we present a novel class of attacks based on this vulnerability that enable policy manipulation and induction in the learning process of DQNs. Read More

We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field, and show that it both has a Gaussian distribution and only occupies a fraction of the full theoretical receptive field. Read More

The combinatorial explosion that plagues planning and reinforcement learning (RL) algorithms can be moderated using state abstraction. Prohibitively large task representations can be condensed such that essential information is preserved, and consequently, solutions are tractably computable. However, exact abstractions, which treat only fully-identical situations as equivalent, fail to present opportunities for abstraction in environments where no two situations are exactly alike. Read More

Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these methods tailor the teacher's guidance to agents with a particular representation or underlying learning scheme, offering effective but specialized teaching procedures. In this work, we explore protocol programs, an agent-agnostic schema for Human-in-the-Loop Reinforcement Learning. Read More

Task-oriented dialogue focuses on conversational agents that participate in user-initiated dialogues on domain-specific topics. In contrast to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented agents usually explicitly model user intent and belief states. This paper examines bypassing such an explicit representation by depending on a latent neural embedding of state and learning selective attention to dialogue history together with copying to incorporate relevant prior context. Read More

Much of work in semantic web relying on Wikipedia as the main source of knowledge often work on static snapshots of the dataset. The full history of Wikipedia revisions, while contains much more useful information, is still difficult to access due to its exceptional volume. To enable further research on this collection, we developed a tool, named Hedera, that efficiently extracts semantic information from Wikipedia revision history datasets. Read More

The promise of compressive sensing (CS) has been offset by two significant challenges. First, real-world data is not exactly sparse in a fixed basis. Second, current high-performance recovery algorithms are slow to converge, which limits CS to either non-real-time applications or scenarios where massive back-end computing is available. Read More

The rapid advancement of machine learning techniques has re-energized research into general artificial intelligence. While the idea of domain-agnostic meta-learning is appealing, this emerging field must come to terms with its relationship to human cognition and the statistics and structure of the tasks humans perform. The position of this article is that only by aligning our agents' abilities and environments with those of humans do we stand a chance at developing general artificial intelligence (GAI). Read More

Credit assignment in traditional recurrent neural networks usually involves back-propagating through a long chain of tied weight matrices. The length of this chain scales linearly with the number of time-steps as the same network is run at each time-step. This creates many problems, such as vanishing gradients, that have been well studied. Read More

We propose Edward, a Turing-complete probabilistic programming language. Edward builds on two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as traditional deep learning. Read More

In this paper we investigate the links between instantiated argumentation systems and the axioms for non-monotonic reasoning described in [9] with the aim of characterising the nature of argument based reasoning. In doing so, we consider two possible interpretations of the consequence relation, and describe which axioms are met by ASPIC+ under each of these interpretations. We then consider the links between these axioms and the rationality postulates. Read More

A fuzzy clustering algorithm for multidimensional data is proposed in this article. The data is described by vectors whose components are linguistic variables defined in an ordinal scale. The obtained results confirm the efficiency of the proposed approach. Read More

Since Leonard Savage's epoch-making memoir, Subjective Expected Utility Theory has been the presumptive model for decision-making. Savage provided an act-based axiomatization of standard expected utility theory. In this article, we provide a Savage-like axiomatization of nonstandard expected utility theory. Read More

We argue that extensibility is a key challenge for knowledge representation. For this purpose, we propose assertional logic - a knowledge model for easier extension with new AI building blocks. In assertional logic, all syntactic objects are categorized as set theoretic constructs including individuals, concepts and operators, and all kinds of knowledge are formalized by equality assertions. Read More

Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features. However, a linear model with just several parameters normally is not demanding in terms of training data. In this paper, we propose an elegant linear model to untangle confounding factors in challenging realistic multichannel signals such as 2D face videos. Read More

Cyber-Physical Systems in general, and Intelligent Transport Systems (ITS) in particular use heterogeneous data sources combined with problem solving expertise in order to make critical decisions that may lead to some form of actions e.g., driver notifications, change of traffic light signals and braking to prevent an accident. Read More

We introduce a technique to produce discriminative context-aware image captions (captions that describe differences between images or visual concepts) using only generic context-agnostic training data (captions that describe a concept or an image in isolation). For example, given images and captions of "siamese cat" and "tiger cat", our system generates language that describes the "siamese cat" in a way that distinguishes it from "tiger cat". We start with a generic language model that is context-agnostic and add a listener to discriminate between closely-related concepts. Read More

In this work, we propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. The resulting optimisation problem can then be tackled using a whole range of continuous optimisation algorithms which have been developed and used in the literature mainly for training. Our approach is general and can be applied to other sequence-to-sequence neural models as well. Read More

We describe an open-source toolkit for neural machine translation (NMT). The toolkit prioritizes efficiency, modularity, and extensibility with the goal of supporting NMT research into model architectures, feature representations, and source modalities, while maintaining competitive performance and reasonable training requirements. The toolkit consists of modeling and translation support, as well as detailed pedagogical documentation about the underlying techniques. Read More

In this paper, a novel architecture for a deep recurrent neural network, residual LSTM is introduced. A plain LSTM has an internal memory cell that can learn long term dependencies of sequential data. It also provides a temporal shortcut path to avoid vanishing or exploding gradients in the temporal domain. Read More

We introduce a simple and accurate neural model for dependency-based semantic role labeling. Our model predicts predicate-argument dependencies relying on states of a bidirectional LSTM encoder. The semantic role labeler achieves respectable performance on English even without any kind of syntactic information and only using local inference. Read More

Higher-order probabilistic programming languages allow programmers to write sophisticated models in machine learning and statistics in a succinct and structured way, but step outside the standard measure-theoretic formalization of probability theory. Programs may use both higher-order functions and continuous distributions, or even define a probability distribution on functions. But standard probability theory cannot support higher-order functions, that is, the category of measurable spaces is not cartesian closed. Read More

The Internet of Things is arriving to our homes or cities through fields already known like Smart Homes, Smart Cities, or Smart Towns. The monitoring of environmental conditions of cities can help to adapt the indoor locations of the cities in order to be more comfortable for people who stay there. A way to improve the indoor conditions is an efficient temperature control, however, it depends on many factors like the different combinations of outdoor temperature and humidity. Read More

Forecasting the flow of crowds is of great importance to traffic management and public safety, and very challenging as it is affected by many complex factors, including spatial dependencies (nearby and distant), temporal dependencies (closeness, period, trend), and external conditions (e.g., weather and events). Read More

The majority of online display ads are served through real-time bidding (RTB) --- each ad display impression is auctioned off in real-time when it is just being generated from a user visit. To place an ad automatically and optimally, it is critical for advertisers to devise a learning algorithm to cleverly bid an ad impression in real-time. Most previous works consider the bid decision as a static optimization problem of either treating the value of each impression independently or setting a bid price to each segment of ad volume. Read More

Despite the recent progress in automatic theorem provers, proof engineers are still suffering from the lack of powerful proof automation. In this position paper we first report our proof strategy language based on a meta-tool approach. Then, we propose an AI-based approach to drastically improve proof automation for Isabelle, while identifying three major challenges we plan to address for this objective. Read More

Multi-task learning (MTL) involves the simultaneous training of two or more related tasks over shared representations. In this work, we apply MTL to audio-visual automatic speech recognition(AV-ASR). Our primary task is to learn a mapping between audio-visual fused features and frame labels obtained from acoustic GMM/HMM model. Read More

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable performance, they often ignore the structure of task. We present a natural representation of to Reinforcement Learning (RL) problems using Recurrent Convolutional Neural Networks (RCNNs), to better exploit this inherent structure. Read More

We present a position paper advocating the notion that Stoic philosophy and ethics can inform the development of ethical A.I. systems. Read More

This paper extends recent work in interactive machine learning (IML) focused on effectively incorporating human feedback. We show how control and feedback signals complement each other in systems which model human reward. We demonstrate that simultaneously incorporating human control and feedback signals can improve interactive robotic systems' performance on a self-mirrored movement control task where an RL-agent controlled right arm attempts to match the preprogrammed movement pattern of the left arm. Read More

Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge. In this work we propose Information Pursuit, a Bayesian framework for scene parsing that combines prior models for the geometry of the scene and the spatial arrangement of objects instances with a data model for the output of high-level image classifiers trained to answer specific questions about the scene. In the proposed framework, the scene interpretation is progressively refined as evidence accumulates from the answers to a sequence of questions. Read More

One of the main problems that emerges in the classic approach to semantics is the difficulty in acquisition and maintenance of ontologies and semantic annotations. On the other hand, the Internet explosion and the massive diffusion of mobile smart devices lead to the creation of a worldwide system, which information is daily checked and fueled by the contribution of millions of users who interacts in a collaborative way. Search engines, continually exploring the Web, are a natural source of information on which to base a modern approach to semantic annotation. Read More

We present a general framework, the coupled compound Poisson factorization (CCPF), to capture the missing-data mechanism in extremely sparse data sets by coupling a hierarchical Poisson factorization with an arbitrary data-generating model. We derive a stochastic variational inference algorithm for the resulting model and, as examples of our framework, implement three different data-generating models---a mixture model, linear regression, and factor analysis---to robustly model non-random missing data in the context of clustering, prediction, and matrix factorization. In all three cases, we test our framework against models that ignore the missing-data mechanism on large scale studies with non-random missing data, and we show that explicitly modeling the missing-data mechanism substantially improves the quality of the results, as measured using data log likelihood on a held-out test set. Read More

Entities are essential elements of natural language. In this paper, we present methods for learning multi-level representations of entities on three complementary levels: character (character patterns in entity names extracted, e.g. Read More

Artificial intelligence has seen a number of breakthroughs in recent years, with games often serving as significant milestones. A common feature of games with these successes is that they involve information symmetry among the players, where all players have identical information. This property of perfect information, though, is far more common in games than in real-world problems. Read More

Artificial intelligence research to a great degree focuses on the brain and behaviors that the brain generates. But the brain, an extremely complex structure resulting from millions of years of evolution, can be viewed as a solution to problems posed by an environment existing in space and time. The environment generates signals that produce sensory events within an organism. Read More

To ease the development of robot learning in industry, two conditions need to be fulfilled. Manipulators must be able to learn high accuracy and precision tasks while being safe for workers in the factory. In this paper, we extend previously submitted work which consists in rapid learning of local high accuracy behaviors. Read More

There is a growing focus on how to design safe artificial intelligent (AI) agents. As systems become more complex, poorly specified goals or control mechanisms may cause AI agents to engage in unwanted and harmful outcomes. Thus it is necessary to design AI agents that follow initial programming intentions as the program grows in complexity. Read More

Two main techniques have been used so far to solve the #P-hard problem #SAT. The first one, used in practice, is based on an extension of DPLL for model counting called exhaustive DPLL. The second approach, more theoretical, exploits the structure of the input to compute the number of satisfying assignments by usually using a dynamic programming scheme on a decomposition of the formula. Read More

In de novo drug design, computational strategies are used to generate novel molecules with good affinity to the desired biological target. In this work, we show that recurrent neural networks can be trained as generative models for molecular structures, similar to statistical language models in natural language processing. We demonstrate that the properties of the generated molecules correlate very well with the properties of the molecules used to train the model. Read More

Existing multi-objective reinforcement learning (MORL) algorithms do not account for objectives that arise from players with differing beliefs. Concretely, consider two players with different beliefs and utility functions who may cooperate to build a machine that takes actions on their behalf. A representation is needed for how much the machine's policy will prioritize each player's interests over time. Read More

In this paper, we study learning generalized driving style representations from automobile GPS trip data. We propose a novel Autoencoder Regularized deep neural Network (ARNet) and a trip encoding framework trip2vec to learn drivers' driving styles directly from GPS records, by combining supervised and unsupervised feature learning in a unified architecture. Experiments on a challenging driver number estimation problem and the driver identification problem show that ARNet can learn a good generalized driving style representation: It significantly outperforms existing methods and alternative architectures by reaching the least estimation error on average (0. Read More

Lifted probabilistic inference (Poole, 2003) and symbolic dynamic programming for lifted stochastic planning (Boutilier et al, 2001) were introduced around the same time as algorithmic efforts to use abstraction in stochastic systems. Over the years, these ideas evolved into two distinct lines of research, each supported by a rich literature. Lifted probabilistic inference focused on efficient arithmetic operations on template-based graphical models under a finite domain assumption while symbolic dynamic programming focused on supporting sequential decision-making in rich quantified logical action models and on open domain reasoning. Read More

Maximizing product use is a central goal of many businesses, which makes retention and monetization two central analytics metrics in games. Player retention may refer to various duration variables quantifying product use: total playtime or session playtime are popular research targets, and active playtime is well-suited for subscription games. Such research often has the goal of increasing player retention or conversely decreasing player churn. Read More

This paper gives complete guidelines for authors submitting papers for the AIRCC Journals. Washing machine is of great domestic necessity as it frees us from the burden of washing our clothes and saves ample of our time. This paper will cover the aspect of designing and developing of Fuzzy Logic based, Smart Washing Machine. Read More

We revisit the notion of probably approximately correct implication bases from the literature and present a first formulation in the language of formal concept analysis, with the goal to investigate whether such bases represent a suitable substitute for exact implication bases in practical use-cases. To this end, we quantitatively examine the behavior of probably approximately correct implication bases on artificial and real-world data sets and compare their precision and recall with respect to their corresponding exact implication bases. Using a small example, we also provide qualitative insight that implications from probably approximately correct bases can still represent meaningful knowledge from a given data set. Read More

The high variance issue in unbiased policy-gradient methods such as VPG and REINFORCE is typically mitigated by adding a baseline. However, the baseline fitting itself suffers from the underfitting or the overfitting problem. In this paper, we develop a K-fold method for baseline estimation in policy gradient algorithms. Read More

In this paper, a non-probabilistic method based on fuzzy logic is used to update finite element models (FEMs). Model updating techniques use the measured data to improve the accuracy of numerical models of structures. However, the measured data are contaminated with experimental noise and the models are inaccurate due to randomness in the parameters. Read More