Showing papers on "Representation (systemics) published in 2017"

The hippocampus as a predictive map

Abstract: The authors show how predictive representations are useful for maximizing future reward, particularly in spatial domains. They develop a predictive-map model of hippocampal place cells and entorhinal grid cells that captures a wide variety of effects from human and rodent literature. A cognitive map has long been the dominant metaphor for hippocampal function, embracing the idea that place cells encode a geometric representation of space. However, evidence for predictive coding, reward sensitivity and policy dependence in place cells suggests that the representation is not purely spatial. We approach this puzzle from a reinforcement learning perspective: what kind of spatial representation is most useful for maximizing future reward? We show that the answer takes the form of a predictive representation. This representation captures many aspects of place cell responses that fall outside the traditional view of a cognitive map. Furthermore, we argue that entorhinal grid cells encode a low-dimensionality basis set for the predictive representation, useful for suppressing noise in predictions and extracting multiscale structure for hierarchical planning.

The Global Rise of Populism: Performance, Political Style, and Representation:

Abstract: of both the setting and the action’ (p. 194), which, among other things, confronts the invisibility of women who for various reasons ‘fall foul of the law’ (p. 196). In the chapter that concludes Part 3, Walters discusses Orange is the New Black (American television series) as a ‘multivalent ... text’ (p. 201), which is not, however, intended for a ‘voyeuristic male getting off on the shower scenes and nudity’ (p. 204). Part 4, ‘Villainesses and anti-antiheroines’, covers three accounts of fictional female figures that do not fit into the antiheroine category, which typically involves a female protagonist displaying moral oscillation that graces her character. Thus, the subject of Joyce’s and La Pastina’s essay is the Brazilian series Salve Jorge (‘Hail George’), with character Lívia Marine (Claudia Raia) who, ‘driven by power and money’ (p. 228) rather than, for example, revenge or vengeance commits horrific crimes against other women and does not display any potentially likeable feminine characteristics of an antiheroine. Another (American) television series that presents female criminals without inherent sympathetic portrayals is The Wire where, as Williams and Press claim, African American women of crime are unfairly denied the nuanced approach that typically connects the audience with the antihero or antiheroine in empathic identification. Redhead’s analysis of Underbelly: Razor concludes the conversation as the author claims that this Australian series is another example of a not so successful portrayal of a television antiheroine: as the narrative focuses on domestic and maternal themes rather than criminal action and public space, the transgressive potential of the story is significantly diluted. The contributors to the book successfully manage to ‘explore atypical portrayals of femininity’ (p. 4) from an international perspective, which is their joint goal as outlined in the Editor’s Introduction. Written for a wide contemporary readership, the book will be of practical use to students of communication and media studies and must not be overlooked by academic philosophers inasmuch as the authors’ discussions contribute to debates on the ontological and existential structures of human existence. Indeed, how do patriarchal gender norms – and attempts to disengage from them – influence our understanding of our own and other people’s selves? It is not easy to escape from these norms: a perceptive reader will note, for example, that the impetus that moves a woman to the position of leadership in organised crime is due to the absence of a man (caused, for example, by death or imprisonment) who would have assumed the leadership role if he was there. The situation where a woman takes on a leadership role when (and only when) a suitable man is not available is not new in human history and in some sense reinforces the patriarchal model of societal organisation.

The successor representation in human reinforcement learning.

Abstract: Theories of reward learning in neuroscience have focused on two families of algorithms thought to capture deliberative versus habitual choice. ‘Model-based’ algorithms compute the value of candidate actions from scratch, whereas ‘model-free’ algorithms make choice more efficient but less flexible by storing pre-computed action values. We examine an intermediate algorithmic family, the successor representation, which balances flexibility and efficiency by storing partially computed action values: predictions about future events. These pre-computation strategies differ in how they update their choices following changes in a task. The successor representation’s reliance on stored predictions about future states predicts a unique signature of insensitivity to changes in the task’s sequence of events, but flexible adjustment following changes to rewards. We provide evidence for such differential sensitivity in two behavioural studies with humans. These results suggest that the successor representation is a computational substrate for semi-flexible choice in humans, introducing a subtler, more cognitive notion of habit. Momennejad et al. formulate and provide evidence for the successor representation, a computational learning mechanism intermediate between the two dominant models (a fast but inflexible ‘model-free’ system and a flexible but slow ‘model-based’ one).

The challenge of abstract concepts.

Abstract: concepts ("freedom") differ from concrete ones ("cat"), as they do not have a bounded, identifiable, and clearly perceivable referent. The way in which abstract concepts are represented has recently become a topic of intense debate, especially because of the spread of the embodied approach to cognition. Within this framework concepts derive their meaning from the same perception, motor, and emotional systems that are involved in online interaction with the world. Most of the evidence in favor of this view, however, has been gathered with regard to concrete concepts. Given the relevance of abstract concepts for higher-order cognition, we argue that being able to explain how they are represented is a crucial challenge that any theory of cognition needs to address. The aim of this article is to offer a critical review of the latest theories on abstract concepts, focusing on embodied ones. Starting with theories that question the distinction between abstract and concrete concepts, we review theories claiming that abstract concepts are grounded in metaphors, in situations and introspection, and in emotion. We then introduce multiple representation theories, according to which abstract concepts evoke both sensorimotor and linguistic information. We argue that the most promising approach is given by multiple representation views that combine an embodied perspective with the recognition of the importance of linguistic and social experience. We conclude by discussing whether or not a single theoretical framework might be able to explain all different varieties of abstract concepts. (PsycINFO Database Record

A map of abstract relational knowledge in the human hippocampal-entorhinal cortex.

Abstract: The hippocampal-entorhinal system encodes a map of space that guides spatial navigation. Goal-directed behaviour outside of spatial navigation similarly requires a representation of abstract forms of relational knowledge. This information relies on the same neural system, but it is not known whether the organisational principles governing continuous maps may extend to the implicit encoding of discrete, non-spatial graphs. Here, we show that the human hippocampal-entorhinal system can represent relationships between objects using a metric that depends on associative strength. We reconstruct a map-like knowledge structure directly from a hippocampal-entorhinal functional magnetic resonance imaging adaptation signal in a situation where relationships are non-spatial rather than spatial, discrete rather than continuous, and unavailable to conscious awareness. Notably, the measure that best predicted a behavioural signature of implicit knowledge and blood oxygen level-dependent adaptation was a weighted sum of future states, akin to the successor representation that has been proposed to account for place and grid-cell firing patterns.

A Compositional Object-Based Approach to Learning Physical Dynamics

Abstract: We present the Neural Physics Engine (NPE), a framework for learning simulators of intuitive physics that naturally generalize across variable object count and different scene configurations. We propose a factorization of a physical scene into composable object-based representations and a neural network architecture whose compositional structure factorizes object dynamics into pairwise interactions. Like a symbolic physics engine, the NPE is endowed with generic notions of objects and their interactions; realized as a neural network, it can be trained via stochastic gradient descent to adapt to specific object properties and dynamics of different worlds. We evaluate the efficacy of our approach on simple rigid body dynamics in two-dimensional worlds. By comparing to less structured architectures, we show that the NPE's compositional representation of the structure in physical interactions improves its ability to predict movement, generalize across variable object count and different scene configurations, and infer latent properties of objects such as mass.

Bi-Level Semantic Representation Analysis for Multimedia Event Detection

Abstract: Multimedia event detection has been one of the major endeavors in video event analysis. A variety of approaches have been proposed recently to tackle this problem. Among others, using semantic representation has been accredited for its promising performance and desirable ability for human-understandable reasoning. To generate semantic representation, we usually utilize several external image/video archives and apply the concept detectors trained on them to the event videos. Due to the intrinsic difference of these archives, the resulted representation is presumable to have different predicting capabilities for a certain event. Notwithstanding, not much work is available for assessing the efficacy of semantic representation from the source-level. On the other hand, it is plausible to perceive that some concepts are noisy for detecting a specific event. Motivated by these two shortcomings, we propose a bi-level semantic representation analyzing method. Regarding source-level, our method learns weights of semantic representation attained from different multimedia archives. Meanwhile, it restrains the negative influence of noisy or irrelevant concepts in the overall concept-level. In addition, we particularly focus on efficient multimedia event detection with few positive examples, which is highly appreciated in the real-world scenario. We perform extensive experiments on the challenging TRECVID MED 2013 and 2014 datasets with encouraging results that validate the efficacy of our proposed approach.

Vectorial representation of spatial goals in the hippocampus of bats

Abstract: To navigate, animals need to represent not only their own position and orientation, but also the location of their goal. Neural representations of an animal’s own position and orientation have been extensively studied. However, it is unknown how navigational goals are encoded in the brain. We recorded from hippocampal CA1 neurons of bats flying in complex trajectories toward a spatial goal. We discovered a subpopulation of neurons with angular tuning to the goal direction. Many of these neurons were tuned to an occluded goal, suggesting that goal-direction representation is memory-based. We also found cells that encoded the distance to the goal, often in conjunction with goal direction. The goal-direction and goal-distance signals make up a vectorial representation of spatial goals, suggesting a previously unrecognized neuronal mechanism for goal-directed navigation.

Integral Human Pose Regression

Abstract: State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as not differentiable and quantization error. This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues. It is differentiable, efficient, and compatible with any heat map based methods. Its effectiveness is convincingly validated via comprehensive ablation experiments under various settings, specifically on 3D pose estimation, for the first time.

A Neural Representation of Sketch Drawings

Abstract: We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundreds of classes. We outline a framework for conditional and unconditional sketch generation, and describe new robust training methods for generating coherent sketch drawings in a vector format.

TransNets: Learning to Transform for Recommendation

Abstract: Recently, deep learning methods have been shown to improve the performance of recommender systems over traditional methods, especially when review text is available. For example, a recent model, DeepCoNN, uses neural nets to learn one latent representation for the text of all reviews written by a target user, and a second latent representation for the text of all reviews for a target item, and then combines these latent representations to obtain state-of-the-art performance on recommendation tasks. We show that (unsurprisingly) much of the predictive value of review text comes from reviews of the target user for the target item. We then introduce a way in which this information can be used in recommendation, even when the target user's review for the target item is not available. Our model, called TransNets, extends the DeepCoNN model by introducing an additional latent layer representing the target user-target item pair. We then regularize this layer, at training time, to be similar to another latent representation of the target user's review of the target item. We show that TransNets and extensions of it improve substantially over the previous state-of-the-art.

The hippocampus as a predictive map

Abstract: A cognitive map has long been the dominant metaphor for hippocampal function, embracing the idea that place cells encode a geometric representation of space. However, evidence for predictive coding, reward sensitivity, and policy dependence in place cells suggests that the representation is not purely spatial. We approach this puzzle from a reinforcement learning perspective: what kind of spatial representation is most useful for maximizing future reward? We show that the answer takes the form of a predictive representation. This representation captures many aspects of place cell responses that fall outside the traditional view of a cognitive map. Furthermore, we argue that entorhinal grid cells encode a low-dimensional basis set for the predictive representation, useful for suppressing noise in predictions and extracting multiscale structure for hierarchical planning.

Neural SLAM: Learning to Explore with External Memory

Abstract: We present an approach for agents to learn representations of a global map from sensor data, to aid their exploration in new environments. To achieve this, we embed procedures mimicking that of traditional Simultaneous Localization and Mapping (SLAM) into the soft attention based addressing of external memory architectures, in which the external memory acts as an internal representation of the environment. This structure encourages the evolution of SLAM-like behaviors inside a completely differentiable deep neural network. We show that this approach can help reinforcement learning agents to successfully explore new environments where long-term memory is essential. We validate our approach in both challenging grid-world environments and preliminary Gazebo experiments. A video of our experiments can be found at: this https URL.

Explicit representation of confidence informs future value-based decisions

Abstract: Every time we make a choice, we maintain an explicit representation of our confidence in that choice. Using eye-tracking and behavioural measures, the authors show that tracking decision uncertainty is helpful in guiding future behaviour.

Hybrid Reward Architecture for Reinforcement Learning

Abstract: One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network. While this approach works well in many domains, in domains where the optimal value function cannot easily be reduced to a low-dimensional representation, learning can be very slow and unstable. This paper contributes towards tackling such challenging domains, by proposing a new method, called Hybrid Reward Architecture (HRA). HRA takes as input a decomposed reward function and learns a separate value function for each component reward function. Because each component typically only depends on a subset of all features, the corresponding value function can be approximated more easily by a low-dimensional representation, enabling more effective learning. We demonstrate HRA on a toy-problem and the Atari game Ms. Pac-Man, where HRA achieves above-human performance.

Representation of Women Among Academic Grand Rounds Speakers.

Abstract: Representation of Women Among Academic Grand Rounds Speakers Grand rounds (GR), a time-honored method of disseminating clinical and research knowledge to medical audiences, showcases speakers as successful academic role models. Exposure to successful female role models, such as GR speakers, may positively affect the retention of women in academic medicine.1,2 In the present study, we sought to determine whether women’s representation as GR speakers reflects their representation in academic medical workforces.

Multi-task Attention-based Neural Networks for Implicit Discourse Relationship Representation and Identification

Abstract: We present a novel multi-task attention based neural network model to address implicit discourse relationship representation and identification through two types of representation learning, an attention based neural network for learning discourse relationship representation with two arguments and a multi-task framework for learning knowledge from annotated and unannotated corpora. The extensive experiments have been performed on two benchmark corpora (i.e., PDTB and CoNLL-2016 datasets). Experimental results show that our proposed model outperforms the state-of-the-art systems on benchmark corpora.

Spatial Memory for Context Reasoning in Object Detection

Abstract: Modeling instance-level context and object-object relationships is extremely challenging. It requires reasoning about bounding boxes of different classes, locations \etc. Above all, instance-level spatial reasoning inherently requires modeling conditional distributions on previous detections. Unfortunately, our current object detection systems do not have any {\bf memory} to remember what to condition on! The state-of-the-art object detectors still detect all object in parallel followed by non-maximal suppression (NMS). While memory has been used for tasks such as captioning, they mostly use image-level memory cells without capturing the spatial layout. On the other hand, modeling object-object relationships requires {\bf spatial} reasoning -- not only do we need a memory to store the spatial layout, but also a effective reasoning module to extract spatial patterns. This paper presents a conceptually simple yet powerful solution -- Spatial Memory Network (SMN), to model the instance-level context efficiently and effectively. Our spatial memory essentially assembles object instances back into a pseudo "image" representation that is easy to be fed into another ConvNet for object-object context reasoning. This leads to a new sequential reasoning architecture where image and memory are processed in parallel to obtain detections which update the memory again. We show our SMN direction is promising as it provides 2.2\% improvement over baseline Faster RCNN on the COCO dataset so far.

Symbolic bordering: The self-representation of migrants and refugees in digital news

Abstract: In this article, I combine theorizations of the selfie as an aesthetic and technological practice of digital self-representation with a theatrical conception of spectatorship, inspired by Adam Smit...

Grayscale-Thermal Object Tracking via Multitask Laplacian Sparse Representation

Abstract: This paper studies the problem of object tracking in challenging scenarios by leveraging multimodal visual data. We propose a grayscale-thermal object tracking method in Bayesian filtering framework based on multitask Laplacian sparse representation. Given one bounding box, we extract a set of overlapping local patches within it, and pursue the multitask joint sparse representation for grayscale and thermal modalities. Then, the representation coefficients of the two modalities are concatenated into a vector to represent the feature of the bounding box. Moreover, the similarity between each patch pair is deployed to refine their representation coefficients in the sparse representation, which can be formulated as the Laplacian sparse representation. We also incorporate the modal reliability into the Laplacian sparse representation to achieve an adaptive fusion of different source data. Experiments on two grayscale-thermal datasets suggest that the proposed approach outperforms both grayscale and grayscale-thermal tracking approaches.

Classification via Sparse Representation of Steerable Wavelet Frames on Grassmann Manifold: Application to Target Recognition in SAR Image

Abstract: Automatic target recognition has been widely studied over the years, yet it is still an open problem. The main obstacle consists in extended operating conditions, e.g. ., depression angle change, configuration variation, articulation, and occlusion. To deal with them, this paper proposes a new classification strategy. We develop a new representation model via the steerable wavelet frames. The proposed representation model is entirely viewed as an element on Grassmann manifolds. To achieve target classification, we embed Grassmann manifolds into an implicit reproducing Kernel Hilbert space (RKHS), where the kernel sparse learning can be applied. Specifically, the mappings of training sample in RKHS are concatenated to form an overcomplete dictionary. It is then used to encode the counterpart of query as a linear combination of its atoms. By designed Grassmann kernel function, it is capable to obtain the sparse representation, from which the inference can be reached. The novelty of this paper comes from: 1) the development of representation model by the set of directional components of Riesz transform; 2) the quantitative measure of similarity for proposed representation model by Grassmann metric; and 3) the generation of global kernel function by Grassmann kernel. Extensive comparative studies are performed to demonstrate the advantage of proposed strategy.

Feature Selection Guided Auto-Encoder

Abstract: Recently the auto-encoder and its variants have demonstrated their promising results in extracting effective features. Specifically, its basic idea of encouraging the output to be as similar as input, ensures the learned representation could faithfully reconstruct the input data. However, one problem arises that not all hidden units are useful to compress the discriminative information while lots of units mainly contribute to represent the task-irrelevant patterns. In this paper, we propose a novel algorithm, Feature Selection Guided Auto-Encoder, which is a unified generative model that integrates feature selection and auto-encoder together. To this end, our proposed algorithm can distinguish the task-relevant units from the task-irrelevant ones to obtain most effective features for future classification tasks. Our model not only performs feature selection on learned high-level features, but also dynamically endows the auto-encoder to produce more discriminative units. Experiments on several benchmarks demonstrate our method's superiority over state-of-the-art approaches.

Adaptive synthesis of indoor scenes via activity-associated object relation graphs

Abstract: We present a system for adaptive synthesis of indoor scenes given an empty room and only a few object categories. Automatically suggesting indoor objects and proper layouts to convert an empty room to a 3D scene is challenging, since it requires interior design knowledge to balance the factors like space, path distance, illumination and object relations, in order to insure the functional plausibility of the synthesized scenes. We exploit a database of 2D floor plans to extract object relations and provide layout examples for scene synthesis. With the labeled human positions and directions in each plan, we detect the activity relations and compute the coexistence frequency of object pairs to construct activity-associated object relation graphs. Given the input room and user-specified object categories, our system first leverages the object relation graphs and the database floor plans to suggest more potential object categories beyond the specified ones to make resulting scenes functionally complete, and then uses the similar plan references to create the layout of synthesized scenes. We show various synthesis results to demonstrate the practicability of our system, and validate its usability via a user study. We also compare our system with the state-of-the-art furniture layout and activity-centric scene representation methods, in terms of functional plausibility and user friendliness.

Protein Ontology (PRO): enhancing and scaling up the representation of protein entities

Abstract: The Protein Ontology (PRO; http://purl.obolibrary.org/obo/pr) formally defines and describes taxon-specific and taxon-neutral protein-related entities in three major areas: proteins related by evolution; proteins produced from a given gene; and protein-containing complexes. PRO thus serves as a tool for referencing protein entities at any level of specificity. To enhance this ability, and to facilitate the comparison of such entities described in different resources, we developed a standardized representation of proteoforms using UniProtKB as a sequence reference and PSI-MOD as a post-translational modification reference. We illustrate its use in facilitating an alignment between PRO and Reactome protein entities. We also address issues of scalability, describing our first steps into the use of text mining to identify protein-related entities, the large-scale import of proteoform information from expert curated resources, and our ability to dynamically generate PRO terms. Web views for individual terms are now more informative about closely-related terms, including for example an interactive multiple sequence alignment. Finally, we describe recent improvement in semantic utility, with PRO now represented in OWL and as a SPARQL endpoint. These developments will further support the anticipated growth of PRO and facilitate discoverability of and allow aggregation of data relating to protein entities.

Modelling complexity in everyday operations: functional resonance in maritime mooring at quay

Abstract: Maritime operations are complex socio-technical activities, with many interacting agents. Such agents are acting based on different, sometimes conflicting, goals. The traditional approach for safety, based on decomposition and bimodality, might lead to ineffective analyses, ignoring the transient and hidden links among activities as they are performed in everyday work. In this sense, the Functional Resonance Analysis Method (FRAM) offers a representation of work-as-done, acknowledging variability as unavoidable and desirable in order to avoid failures and maintain production. This paper adopts FRAM in combination with an Abstraction/Agency framework to understand and contribute with new perspectives to the complexity of processes. This approach, in line with the principles of Resilience Engineering, is adopted in the traditionally underspecified operation of mooring at quay. The detailed model confirms the benefits of FRAM in representing complex highly coupled tasks, especially in combination with an analysis at different levels of abstractions. The outcomes of the study show how a FRAM model offers systemic and punctual insights for understanding emergent criticalities, analysing complex incident scenarios, identifying potential mitigating actions, exploring different varieties of work and gaining systemic knowledge.

Unsupervised Multi-Manifold Clustering by Learning Deep Representation.

Abstract: In this paper, we propose a novel deep manifold clustering (DMC) method for learning effective deep representations and partitioning a dataset into clusters where each cluster contains data points from a single nonlinear manifold. Different from other previous research efforts, we adopt deep neural network to classify and parameterize unlabeled data which lie on multiple manifolds. Firstly, motivated by the observation that nearby points lie on the local of manifold should possess similar representations, a locality preserving objective is defined to iteratively explore data relation and learn structure preserving representations. Secondly, by finding the corresponding cluster centers from the representations, a clustering-oriented objective is then proposed to guide the model to extract both discriminative and clusterspecific representations. Finally, by integrating two objectives into a single model with a unified cost function and optimizing it by using back propagation, we can obtain not only more powerful representations, but also more precise clusters of data. In addition, our model can be intuitively extended to cluster out-of-sample datum. The experimental results and comparisons with existing state-of-the-art methods show that the proposed method consistently achieves the best performance on various benchmark datasets.

Group-wise Deep Co-saliency Detection

Abstract: In this paper, we propose an end-to-end group-wise deep co-saliency detection approach to address the co-salient object discovery problem based on the fully convolutional network (FCN) with group input and group output. The proposed approach captures the group-wise interaction information for group images by learning a semantics-aware image representation based on a convolutional neural network, which adaptively learns the group-wise features for co-saliency detection. Furthermore, the proposed approach discovers the collaborative and interactive relationships between group-wise feature representation and single-image individual feature representation, and model this in a collaborative learning framework. Finally, we set up a unified end-to-end deep learning scheme to jointly optimize the process of group-wise feature representation learning and the collaborative learning, leading to more reliable and robust co-saliency detection results. Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.

Structural priming in bilinguals

Abstract: In this review, we examine how structural priming has been used to investigate the representation of first and second language syntactic structures in bilinguals. Most experiments suggest that structures that are identical in the first and second language have a single, shared mental representation. The results from structures that are similar but not fully identical are less clear, but they may be explained by assuming that first and second language representations are merely connected rather than fully shared. Some research has also used structural priming to investigate the representation of cognate words. We will also consider whether cross-linguistic structural priming taps into long-term implicit learning effects. Finally, we discuss recent research that has investigated how second language syntactic representations develop as learners’ proficiency increases.

Presenting and representing others: towards an ethics of engagement

Abstract: The ethics of research representation are rarely discussed. Yet representation can have a significant impact on research participants and audiences. This paper draws on some of the limited body of ...