Paper Group ANR 777
Brain decoding from functional MRI using long short-term memory recurrent neural networks. f-CNN$^{\text{x}}$: A Toolflow for Mapping Multiple Convolutional Neural Networks on FPGAs. Analysis of regularized Nyström subsampling for regression functions of low smoothness. Adversarially Robust Optimization with Gaussian Processes. A Variational Time S …
Brain decoding from functional MRI using long short-term memory recurrent neural networks
| Title | Brain decoding from functional MRI using long short-term memory recurrent neural networks |
| Authors | Hongming Li, Yong Fan |
| Abstract | Decoding brain functional states underlying different cognitive processes using multivariate pattern recognition techniques has attracted increasing interests in brain imaging studies. Promising performance has been achieved using brain functional connectivity or brain activation signatures for a variety of brain decoding tasks. However, most of existing studies have built decoding models upon features extracted from imaging data at individual time points or temporal windows with a fixed interval, which might not be optimal across different cognitive processes due to varying temporal durations and dependency of different cognitive processes. In this study, we develop a deep learning based framework for brain decoding by leveraging recent advances in sequence modeling using long short-term memory (LSTM) recurrent neural networks (RNNs). Particularly, functional profiles extracted from task functional imaging data based on their corresponding subject-specific intrinsic functional networks are used as features to build brain decoding models, and LSTM RNNs are adopted to learn decoding mappings between functional profiles and brain states. We evaluate the proposed method using task fMRI data from the HCP dataset, and experimental results have demonstrated that the proposed method could effectively distinguish brain states under different task events and obtain higher accuracy than conventional decoding models. |
| Tasks | Brain Decoding |
| Published | 2018-09-14 |
| URL | http://arxiv.org/abs/1809.05561v1 |
| http://arxiv.org/pdf/1809.05561v1.pdf | |
| PWC | https://paperswithcode.com/paper/brain-decoding-from-functional-mri-using-long |
| Repo | |
| Framework | |
f-CNN$^{\text{x}}$: A Toolflow for Mapping Multiple Convolutional Neural Networks on FPGAs
| Title | f-CNN$^{\text{x}}$: A Toolflow for Mapping Multiple Convolutional Neural Networks on FPGAs |
| Authors | Stylianos I. Venieris, Christos-Savvas Bouganis |
| Abstract | The predictive power of Convolutional Neural Networks (CNNs) has been an integral factor for emerging latency-sensitive applications, such as autonomous drones and vehicles. Such systems employ multiple CNNs, each one trained for a particular task. The efficient mapping of multiple CNNs on a single FPGA device is a challenging task as the allocation of compute resources and external memory bandwidth needs to be optimised at design time. This paper proposes f-CNN$^{\text{x}}$, an automated toolflow for the optimised mapping of multiple CNNs on FPGAs, comprising a novel multi-CNN hardware architecture together with an automated design space exploration method that considers the user-specified performance requirements for each model to allocate compute resources and generate a synthesisable accelerator. Moreover, f-CNN$^{\text{x}}$ employs a novel scheduling algorithm that alleviates the limitations of the memory bandwidth contention between CNNs and sustains the high utilisation of the architecture. Experimental evaluation shows that f-CNN$^{\text{x}}$'s designs outperform contention-unaware FPGA mappings by up to 50% and deliver up to 6.8x higher performance-per-Watt over highly optimised GPU designs for multi-CNN systems. |
| Tasks | |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10174v1 |
| http://arxiv.org/pdf/1805.10174v1.pdf | |
| PWC | https://paperswithcode.com/paper/f-cnntextx-a-toolflow-for-mapping-multiple |
| Repo | |
| Framework | |
Analysis of regularized Nyström subsampling for regression functions of low smoothness
| Title | Analysis of regularized Nyström subsampling for regression functions of low smoothness |
| Authors | Shuai Lu, Peter Mathé, Sergiy Pereverzyev Jr |
| Abstract | This paper studies a Nystr"om type subsampling approach to large kernel learning methods in the misspecified case, where the target function is not assumed to belong to the reproducing kernel Hilbert space generated by the underlying kernel. This case is less understood, in spite of its practical importance. To model such a case, the smoothness of target functions is described in terms of general source conditions. It is surprising that almost for the whole range of the source conditions, describing the misspecified case, the corresponding learning rate bounds can be achieved with just one value of the regularization parameter. This observation allows a formulation of mild conditions under which the plain Nystr"om subsampling can be realized with subquadratic cost maintaining the guaranteed learning rates. |
| Tasks | |
| Published | 2018-06-03 |
| URL | http://arxiv.org/abs/1806.00826v1 |
| http://arxiv.org/pdf/1806.00826v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-regularized-nystrom-subsampling |
| Repo | |
| Framework | |
Adversarially Robust Optimization with Gaussian Processes
| Title | Adversarially Robust Optimization with Gaussian Processes |
| Authors | Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, Volkan Cevher |
| Abstract | In this paper, we consider the problem of Gaussian process (GP) optimization with an added robustness requirement: The returned point may be perturbed by an adversary, and we require the function value to remain as high as possible even after this perturbation. This problem is motivated by settings in which the underlying functions during optimization and implementation stages are different, or when one is interested in finding an entire region of good inputs rather than only a single point. We show that standard GP optimization algorithms do not exhibit the desired robustness properties, and provide a novel confidence-bound based algorithm StableOpt for this purpose. We rigorously establish the required number of samples for StableOpt to find a near-optimal point, and we complement this guarantee with an algorithm-independent lower bound. We experimentally demonstrate several potential applications of interest using real-world data sets, and we show that StableOpt consistently succeeds in finding a stable maximizer where several baseline methods fail. |
| Tasks | Gaussian Processes |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.10775v2 |
| http://arxiv.org/pdf/1810.10775v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarially-robust-optimization-with |
| Repo | |
| Framework | |
A Variational Time Series Feature Extractor for Action Prediction
| Title | A Variational Time Series Feature Extractor for Action Prediction |
| Authors | Maxime Chaveroche, Adrien Malaisé, Francis Colas, François Charpillet, Serena Ivaldi |
| Abstract | We propose a Variational Time Series Feature Extractor (VTSFE), inspired by the VAE-DMP model of Chen et al., to be used for action recognition and prediction. Our method is based on variational autoencoders. It improves VAE-DMP in that it has a better noise inference model, a simpler transition model constraining the acceleration in the trajectories of the latent space, and a tighter lower bound for the variational inference. We apply the method for classification and prediction of whole-body movements on a dataset with 7 tasks and 10 demonstrations per task, recorded with a wearable motion capture suit. The comparison with VAE and VAE-DMP suggests the better performance of our method for feature extraction. An open-source software implementation of each method with TensorFlow is also provided. In addition, a more detailed version of this work can be found in the indicated code repository. Although it was meant to, the VTSFE hasn’t been tested for action prediction, due to a lack of time in the context of Maxime Chaveroche’s Master thesis at INRIA. |
| Tasks | Motion Capture, Temporal Action Localization, Time Series |
| Published | 2018-07-06 |
| URL | http://arxiv.org/abs/1807.02350v2 |
| http://arxiv.org/pdf/1807.02350v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-variational-time-series-feature-extractor |
| Repo | |
| Framework | |
Theoretical Analysis of Sparse Subspace Clustering with Missing Entries
| Title | Theoretical Analysis of Sparse Subspace Clustering with Missing Entries |
| Authors | Manolis C. Tsakiris, Rene Vidal |
| Abstract | Sparse Subspace Clustering (SSC) is a popular unsupervised machine learning method for clustering data lying close to an unknown union of low-dimensional linear subspaces; a problem with numerous applications in pattern recognition and computer vision. Even though the behavior of SSC for complete data is by now well-understood, little is known about its theoretical properties when applied to data with missing entries. In this paper we give theoretical guarantees for SSC with incomplete data, and analytically establish that projecting the zero-filled data onto the observation pattern of the point being expressed leads to a substantial improvement in performance. The main insight that stems from our analysis is that even though the projection induces additional missing entries, this is counterbalanced by the fact that the projected and zero-filled data are in effect incomplete points associated with the union of the corresponding projected subspaces, with respect to which the point being expressed is complete. The significance of this phenomenon potentially extends to the entire class of self-expressive methods. |
| Tasks | |
| Published | 2018-01-01 |
| URL | http://arxiv.org/abs/1801.00393v3 |
| http://arxiv.org/pdf/1801.00393v3.pdf | |
| PWC | https://paperswithcode.com/paper/theoretical-analysis-of-sparse-subspace |
| Repo | |
| Framework | |
Identifying and Controlling Important Neurons in Neural Machine Translation
| Title | Identifying and Controlling Important Neurons in Neural Machine Translation |
| Authors | Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James Glass |
| Abstract | Neural machine translation (NMT) models learn representations containing substantial linguistic information. However, it is not clear if such information is fully distributed or if some of it can be attributed to individual neurons. We develop unsupervised methods for discovering important neurons in NMT models. Our methods rely on the intuition that different models learn similar properties, and do not require any costly external supervision. We show experimentally that translation quality depends on the discovered neurons, and find that many of them capture common linguistic phenomena. Finally, we show how to control NMT translations in predictable ways, by modifying activations of individual neurons. |
| Tasks | Machine Translation |
| Published | 2018-11-03 |
| URL | http://arxiv.org/abs/1811.01157v1 |
| http://arxiv.org/pdf/1811.01157v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-and-controlling-important-neurons |
| Repo | |
| Framework | |
Coronary Artery Centerline Extraction in Cardiac CT Angiography Using a CNN-Based Orientation Classifier
| Title | Coronary Artery Centerline Extraction in Cardiac CT Angiography Using a CNN-Based Orientation Classifier |
| Authors | Jelmer M. Wolterink, Robbert W. van Hamersvelt, Max A. Viergever, Tim Leiner, Ivana Išgum |
| Abstract | Coronary artery centerline extraction in cardiac CT angiography (CCTA) images is a prerequisite for evaluation of stenoses and atherosclerotic plaque. We propose an algorithm that extracts coronary artery centerlines in CCTA using a convolutional neural network (CNN). A 3D dilated CNN is trained to predict the most likely direction and radius of an artery at any given point in a CCTA image based on a local image patch. Starting from a single seed point placed manually or automatically anywhere in a coronary artery, a tracker follows the vessel centerline in two directions using the predictions of the CNN. Tracking is terminated when no direction can be identified with high certainty. The CNN was trained using 32 manually annotated centerlines in a training set consisting of 8 CCTA images provided in the MICCAI 2008 Coronary Artery Tracking Challenge (CAT08). Evaluation using 24 test images of the CAT08 challenge showed that extracted centerlines had an average overlap of 93.7% with 96 manually annotated reference centerlines. Extracted centerline points were highly accurate, with an average distance of 0.21 mm to reference centerline points. In a second test set consisting of 50 CCTA scans, 5,448 markers in the coronary arteries were used as seed points to extract single centerlines. This showed strong correspondence between extracted centerlines and manually placed markers. In a third test set containing 36 CCTA scans, fully automatic seeding and centerline extraction led to extraction of on average 92% of clinically relevant coronary artery segments. The proposed method is able to accurately and efficiently determine the direction and radius of coronary arteries. The method can be trained with limited training data, and once trained allows fast automatic or interactive extraction of coronary artery trees from CCTA images. |
| Tasks | |
| Published | 2018-10-07 |
| URL | http://arxiv.org/abs/1810.03143v2 |
| http://arxiv.org/pdf/1810.03143v2.pdf | |
| PWC | https://paperswithcode.com/paper/coronary-artery-centerline-extraction-in |
| Repo | |
| Framework | |
Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data
| Title | Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data |
| Authors | Noshaba Cheema, Somayeh Hosseini, Janis Sprenger, Erik Herrmann, Han Du, Klaus Fischer, Philipp Slusallek |
| Abstract | Semantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion capture sequences are partitioned into smaller segments. Afterwards, additional methods like statistical modeling can be applied to each group of structurally-similar segments to learn an abstract motion manifold. The segmentation task however often remains a manual task, which increases the effort and cost of generating large-scale motion databases. We therefore propose an automatic framework for semantic segmentation of motion capture data using a dilated temporal fully-convolutional network. Our model outperforms a state-of-the-art model in action segmentation, as well as three networks for sequence modeling. We further show our model is robust against high noisy training labels. |
| Tasks | action segmentation, Motion Capture, Semantic Segmentation |
| Published | 2018-06-24 |
| URL | http://arxiv.org/abs/1806.09174v1 |
| http://arxiv.org/pdf/1806.09174v1.pdf | |
| PWC | https://paperswithcode.com/paper/dilated-temporal-fully-convolutional-network |
| Repo | |
| Framework | |
Deep Multiple Instance Feature Learning via Variational Autoencoder
| Title | Deep Multiple Instance Feature Learning via Variational Autoencoder |
| Authors | Shabnam Ghaffarzadegan |
| Abstract | We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised learning problem where labels are associated with groups of instances (referred as bags) instead of individual instances. To address the essential challenge in MIL problems raised from the uncertainty of positive instances label, we use a discriminative model regularized by variational autoencoders (VAEs) to maximize the differences between latent representations of all instances and negative instances. As a result, the hidden layer of the variational autoencoder learns meaningful representation. This representation can effectively be used for MIL problems as illustrated by better performance on the standard benchmark datasets comparing to the state-of-the-art approaches. More importantly, unlike most related studies, the proposed framework can be easily scaled to large dataset problems, as illustrated by the audio event detection and segmentation task. Visualization also confirms the effectiveness of the latent representation in discriminating positive and negative classes. |
| Tasks | Multiple Instance Learning |
| Published | 2018-07-06 |
| URL | http://arxiv.org/abs/1807.02490v1 |
| http://arxiv.org/pdf/1807.02490v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multiple-instance-feature-learning-via |
| Repo | |
| Framework | |
An Integrated Framework for AI Assisted Level Design in 2D Platformers
| Title | An Integrated Framework for AI Assisted Level Design in 2D Platformers |
| Authors | Antonio Umberto Aramini, Pier Luca Lanzi, Daniele Loiacono |
| Abstract | The design of video game levels is a complex and critical task. Levels need to elicit fun and challenge while avoiding frustration at all costs. In this paper, we present a framework to assist designers in the creation of levels for 2D platformers. Our framework provides designers with a toolbox (i) to create 2D platformer levels, (ii) to estimate the difficulty and probability of success of single jump actions (the main mechanics of platformer games), and (iii) a set of metrics to evaluate the difficulty and probability of completion of entire levels. At the end, we present the results of a set of experiments we carried out with human players to validate the metrics included in our framework. |
| Tasks | |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.09153v1 |
| http://arxiv.org/pdf/1804.09153v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-integrated-framework-for-ai-assisted-level |
| Repo | |
| Framework | |
Generalizing the theory of cooperative inference
| Title | Generalizing the theory of cooperative inference |
| Authors | Pei Wang, Pushpi Paranamana, Patrick Shafto |
| Abstract | Cooperation information sharing is important to theories of human learning and has potential implications for machine learning. Prior work derived conditions for achieving optimal Cooperative Inference given strong, relatively restrictive assumptions. We relax these assumptions by demonstrating convergence for any discrete joint distribution, robustness through equivalence classes and stability under perturbation, and effectiveness by deriving bounds from structural properties of the original joint distribution. We provide geometric interpretations, connections to and implications for optimal transport, and connections to importance sampling, and conclude by outlining open questions and challenges to realizing the promise of Cooperative Inference. |
| Tasks | |
| Published | 2018-10-04 |
| URL | http://arxiv.org/abs/1810.02423v2 |
| http://arxiv.org/pdf/1810.02423v2.pdf | |
| PWC | https://paperswithcode.com/paper/generalizing-the-theory-of-cooperative |
| Repo | |
| Framework | |
Disentangled VAE Representations for Multi-Aspect and Missing Data
| Title | Disentangled VAE Representations for Multi-Aspect and Missing Data |
| Authors | Samuel K. Ainsworth, Nicholas J. Foti, Emily B. Fox |
| Abstract | Many problems in machine learning and related application areas are fundamentally variants of conditional modeling and sampling across multi-aspect data, either multi-view, multi-modal, or simply multi-group. For example, sampling from the distribution of English sentences conditioned on a given French sentence or sampling audio waveforms conditioned on a given piece of text. Central to many of these problems is the issue of missing data: we can observe many English, French, or German sentences individually but only occasionally do we have data for a sentence pair. Motivated by these applications and inspired by recent progress in variational autoencoders for grouped data, we develop factVAE, a deep generative model capable of handling multi-aspect data, robust to missing observations, and with a prior that encourages disentanglement between the groups and the latent dimensions. The effectiveness of factVAE is demonstrated on a variety of rich real-world datasets, including motion capture poses and pictures of faces captured from varying poses and perspectives. |
| Tasks | Motion Capture |
| Published | 2018-06-24 |
| URL | http://arxiv.org/abs/1806.09060v1 |
| http://arxiv.org/pdf/1806.09060v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangled-vae-representations-for-multi |
| Repo | |
| Framework | |
Learning Hierarchical Item Categories from Implicit Feedback Data for Efficient Recommendations and Browsing
| Title | Learning Hierarchical Item Categories from Implicit Feedback Data for Efficient Recommendations and Browsing |
| Authors | Farhan Khawar, Nevin L. Zhang |
| Abstract | Searching, browsing, and recommendations are common ways in which the “choice overload” faced by users in the online marketplace can be mitigated. In this paper we propose the use of hierarchical item categories, obtained from implicit feedback data, to enable efficient browsing and recommendations. We present a method of creating hierarchical item categories from implicit feedback data only i.e., without any other information on the items like name, genre etc. Categories created in this fashion are based on users’ co-consumption of items. Thus, they can be more useful for users in finding interesting and relevant items while they are browsing through the hierarchy. We also show that this item hierarchy can be useful in making category based recommendations, which makes the recommendations more explainable and increases the diversity of the recommendations without compromising much on the accuracy. Item hierarchy can also be useful in the creation of an automatic item taxonomy skeleton by bypassing manual labeling and annotation. This can especially be useful for small vendors. Our data-driven hierarchical categories are based on hierarchical latent tree analysis (HLTA) which has been previously used for text analysis. We present a scaled up learning algorithm \emph{HLTA-Forest} so that HLTA can be applied to implicit feedback data. |
| Tasks | |
| Published | 2018-06-06 |
| URL | https://arxiv.org/abs/1806.02056v2 |
| https://arxiv.org/pdf/1806.02056v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-hierarchical-item-categories-from |
| Repo | |
| Framework | |
Concept2vec: Metrics for Evaluating Quality of Embeddings for Ontological Concepts
| Title | Concept2vec: Metrics for Evaluating Quality of Embeddings for Ontological Concepts |
| Authors | Faisal Alshargi, Saeedeh Shekarpour, Tommaso Soru, Amit Sheth |
| Abstract | Although there is an emerging trend towards generating embeddings for primarily unstructured data, and recently for structured data, there is not yet any systematic suite for measuring the quality of embeddings. This deficiency is further sensed with respect to embeddings generated for structured data because there are no concrete evaluation metrics measuring the quality of encoded structure as well as semantic patterns in the embedding space. In this paper, we introduce a framework containing three distinct tasks concerned with the individual aspects of ontological concepts: (i) the categorization aspect, (ii) the hierarchical aspect, and (iii) the relational aspect. Then, in the scope of each task, a number of intrinsic metrics are proposed for evaluating the quality of the embeddings. Furthermore, w.r.t. this framework multiple experimental studies were run to compare the quality of the available embedding models. Employing this framework in future research can reduce misjudgment and provide greater insight about quality comparisons of embeddings for ontological concepts. |
| Tasks | |
| Published | 2018-03-12 |
| URL | http://arxiv.org/abs/1803.04488v2 |
| http://arxiv.org/pdf/1803.04488v2.pdf | |
| PWC | https://paperswithcode.com/paper/concept2vec-metrics-for-evaluating-quality-of |
| Repo | |
| Framework | |
