Paper Group ANR 935
Integrating Artificial Intelligence with Real-time Intracranial EEG Monitoring to Automate Interictal Identification of Seizure Onset Zones in Focal Epilepsy. Design and software implementation of subsystems for creating and using the ontological base of a research scientist. Latent Variable Model for Multi-modal Translation. Can everyday AI be eth …
Integrating Artificial Intelligence with Real-time Intracranial EEG Monitoring to Automate Interictal Identification of Seizure Onset Zones in Focal Epilepsy
Title | Integrating Artificial Intelligence with Real-time Intracranial EEG Monitoring to Automate Interictal Identification of Seizure Onset Zones in Focal Epilepsy |
Authors | Yogatheesan Varatharajah, Brent Berry, Jan Cimbalnik, Vaclav Kremen, Jamie Van Gompel, Matt Stead, Benjamin Brinkmann, Ravishankar Iyer, Gregory Worrell |
Abstract | An ability to map seizure-generating brain tissue, i.e., the seizure onset zone (SOZ), without recording actual seizures could reduce the duration of invasive EEG monitoring for patients with drug-resistant epilepsy. A widely-adopted practice in the literature is to compare the incidence (events/time) of putative pathological electrophysiological biomarkers associated with epileptic brain tissue with the SOZ determined from spontaneous seizures recorded with intracranial EEG, primarily using a single biomarker. Clinical translation of the previous efforts suffers from their inability to generalize across multiple patients because of (a) the inter-patient variability and (b) the temporal variability in the epileptogenic activity. Here, we report an artificial intelligence-based approach for combining multiple interictal electrophysiological biomarkers and their temporal characteristics as a way of accounting for the above barriers and show that it can reliably identify seizure onset zones in a study cohort of 82 patients who underwent evaluation for drug-resistant epilepsy. Our investigation provides evidence that utilizing the complementary information provided by multiple electrophysiological biomarkers and their temporal characteristics can significantly improve the localization potential compared to previously published single-biomarker incidence-based approaches, resulting in an average area under ROC curve (AUC) value of 0.73 in a cohort of 82 patients. Our results also suggest that recording durations between ninety minutes and two hours are sufficient to localize SOZs with accuracies that may prove clinically relevant. The successful validation of our approach on a large cohort of 82 patients warrants future investigation on the feasibility of utilizing intra-operative EEG monitoring and artificial intelligence to localize epileptogenic brain tissue. |
Tasks | EEG |
Published | 2018-12-15 |
URL | http://arxiv.org/abs/1812.06234v1 |
http://arxiv.org/pdf/1812.06234v1.pdf | |
PWC | https://paperswithcode.com/paper/integrating-artificial-intelligence-with-real |
Repo | |
Framework | |
Design and software implementation of subsystems for creating and using the ontological base of a research scientist
Title | Design and software implementation of subsystems for creating and using the ontological base of a research scientist |
Authors | O. V. Palagin, K. S. Malakhov, V. Yu. Velichko, O. S. Shurov |
Abstract | Creation of the information systems and tools for scientific research and development support has always been one of the central directions of the development of computer science. The main features of the modern evolution of scientific research and development are the transdisciplinary approach and the deep intellectualisation of all stages of the life cycle of formulation and solution of scientific problems. The theoretical and practical aspects of the development of perspective complex knowledge-oriented information systems and their components are considered in the paper. The analysis of existing scientific information systems (or current research information systems, CRIS) and synthesis of general principles of design of the research and development workstation environment of a researcher and its components are carried out in the work. The functional components of knowledge-oriented information system research and development workstation environment of a researcher are designed. Designed and developed functional components of knowledge-oriented information system developing research and development workstation environment,including functional models and software implementation of the software subsystem for creation and use of ontological knowledge base for research fellow publications, as part of personalized knowledge base of scientific researcher. Research in modern conditions of e-Science paradigm requires pooling scientific community and intensive exchange of research results that may be achieved through the use of scientific information systems. research and development workstation environment allows to solve problems of contructivisation and formalisation of knowledge representation, obtained during the research process and collective accomplices interaction. |
Tasks | |
Published | 2018-02-17 |
URL | http://arxiv.org/abs/1802.06768v2 |
http://arxiv.org/pdf/1802.06768v2.pdf | |
PWC | https://paperswithcode.com/paper/design-and-software-implementation-of |
Repo | |
Framework | |
Latent Variable Model for Multi-modal Translation
Title | Latent Variable Model for Multi-modal Translation |
Authors | Iacer Calixto, Miguel Rios, Wilker Aziz |
Abstract | In this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be seen as a multi-modal stochastic embedding of an image and its description in a foreign language. It is used in a target-language decoder and also to predict image features. Importantly, our model formulation utilises visual and textual inputs during training but does not require that images be available at test time. We show that our latent variable MMT formulation improves considerably over strong baselines, including a multi-task learning approach (Elliott and K'ad'ar, 2017) and a conditional variational auto-encoder approach (Toyama et al., 2016). Finally, we show improvements due to (i) predicting image features in addition to only conditioning on them, (ii) imposing a constraint on the minimum amount of information encoded in the latent variable, and (iii) by training on additional target-language image descriptions (i.e. synthetic data). |
Tasks | Machine Translation, Multi-Task Learning |
Published | 2018-11-01 |
URL | https://arxiv.org/abs/1811.00357v2 |
https://arxiv.org/pdf/1811.00357v2.pdf | |
PWC | https://paperswithcode.com/paper/latent-visual-cues-for-neural-machine |
Repo | |
Framework | |
Can everyday AI be ethical. Fairness of Machine Learning Algorithms
Title | Can everyday AI be ethical. Fairness of Machine Learning Algorithms |
Authors | Philippe Besse, Celine Castets-Renard, Aurelien Garivier, Jean-Michel Loubes |
Abstract | Combining big data and machine learning algorithms, the power of automatic decision tools induces as much hope as fear. Many recently enacted European legislation (GDPR) and French laws attempt to regulate the use of these tools. Leaving aside the well-identified problems of data confidentiality and impediments to competition, we focus on the risks of discrimination, the problems of transparency and the quality of algorithmic decisions. The detailed perspective of the legal texts, faced with the complexity and opacity of the learning algorithms, reveals the need for important technological disruptions for the detection or reduction of the discrimination risk, and for addressing the right to obtain an explanation of the auto- matic decision. Since trust of the developers and above all of the users (citizens, litigants, customers) is essential, algorithms exploiting personal data must be deployed in a strict ethical framework. In conclusion, to answer this need, we list some ways of controls to be developed: institutional control, ethical charter, external audit attached to the issue of a label. |
Tasks | |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.01729v1 |
http://arxiv.org/pdf/1810.01729v1.pdf | |
PWC | https://paperswithcode.com/paper/can-everyday-ai-be-ethical-fairness-of |
Repo | |
Framework | |
client2vec: Towards Systematic Baselines for Banking Applications
Title | client2vec: Towards Systematic Baselines for Banking Applications |
Authors | Leonardo Baldassini, Jose Antonio Rodríguez Serrano |
Abstract | The workflow of data scientists normally involves potentially inefficient processes such as data mining, feature engineering and model selection. Recent research has focused on automating this workflow, partly or in its entirety, to improve productivity. We choose the former approach and in this paper share our experience in designing the client2vec: an internal library to rapidly build baselines for banking applications. Client2vec uses marginalized stacked denoising autoencoders on current account transactions data to create vector embeddings which represent the behaviors of our clients. These representations can then be used in, and optimized against, a variety of tasks such as client segmentation, profiling and targeting. Here we detail how we selected the algorithmic machinery of client2vec and the data it works on and present experimental results on several business cases. |
Tasks | Denoising, Feature Engineering, Model Selection |
Published | 2018-02-12 |
URL | http://arxiv.org/abs/1802.04198v1 |
http://arxiv.org/pdf/1802.04198v1.pdf | |
PWC | https://paperswithcode.com/paper/client2vec-towards-systematic-baselines-for |
Repo | |
Framework | |
Deep Energies for Estimating Three-Dimensional Facial Pose and Expression
Title | Deep Energies for Estimating Three-Dimensional Facial Pose and Expression |
Authors | Michael Bao, Jane Wu, Xinwei Yao, Ronald Fedkiw |
Abstract | While much progress has been made in capturing high-quality facial performances using motion capture markers and shape-from-shading, high-end systems typically also rely on rotoscope curves hand-drawn on the image. These curves are subjective and difficult to draw consistently; moreover, ad-hoc procedural methods are required for generating matching rotoscope curves on synthetic renders embedded in the optimization used to determine three-dimensional facial pose and expression. We propose an alternative approach whereby these curves and other keypoints are detected automatically on both the image and the synthetic renders using trained neural networks, eliminating artist subjectivity and the ad-hoc procedures meant to mimic it. More generally, we propose using machine learning networks to implicitly define deep energies which when minimized using classical optimization techniques lead to three-dimensional facial pose and expression estimation. |
Tasks | Motion Capture |
Published | 2018-12-07 |
URL | http://arxiv.org/abs/1812.02899v1 |
http://arxiv.org/pdf/1812.02899v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-energies-for-estimating-three |
Repo | |
Framework | |
NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning
Title | NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning |
Authors | Sirui Xie, Junning Huang, Lanxin Lei, Chunxiao Liu, Zheng Ma, Wei Zhang, Liang Lin |
Abstract | Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that is inherently consistent through a period of time is in desire, especially for tasks with either sparse rewards or long term information. In this work, we introduce a novel on-policy temporally consistent exploration strategy - Neural Adaptive Dropout Policy Exploration (NADPEx) - for deep reinforcement learning agents. Modeled as a global random variable for conditional distribution, dropout is incorporated to reinforcement learning policies, equipping them with inherent temporal consistency, even when the reward signals are sparse. Two factors, gradients’ alignment with the objective and KL constraint in policy space, are discussed to guarantee NADPEx policy’s stable improvement. Our experiments demonstrate that NADPEx solves tasks with sparse reward while naive exploration and parameter noise fail. It yields as well or even faster convergence in the standard mujoco benchmark for continuous control. |
Tasks | Continuous Control |
Published | 2018-12-21 |
URL | http://arxiv.org/abs/1812.09028v2 |
http://arxiv.org/pdf/1812.09028v2.pdf | |
PWC | https://paperswithcode.com/paper/nadpex-an-on-policy-temporally-consistent |
Repo | |
Framework | |
Approximate Random Dropout
Title | Approximate Random Dropout |
Authors | Zhuoran Song, Ru Wang, Dongyu Ru, Hongru Huang, Zhenghao Peng, Jing Ke, Xiaoyao Liang, Li Jiang |
Abstract | The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in the training phase because the training phase involves dense matrix-multiplication using General Purpose Computation on Graphics Processors (GPGPU), which endorse regular and structural data layout. In this paper, we propose the Approximate Random Dropout that replaces the conventional random dropout of neurons and synapses with a regular and predefined patterns to eliminate the unnecessary computation and data access. To compensate the potential performance loss we develop a SGD-based Search Algorithm to produce the distribution of dropout patterns. We prove our approach is statistically equivalent to the previous dropout method. Experiments results on MLP and LSTM using well-known benchmarks show that the proposed Approximate Random Dropout can reduce the training time by $20%$-$77%$ ($19%$-$60%$) when dropout rate is $0.3$-$0.7$ on MLP (LSTM) with marginal accuracy drop. |
Tasks | |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.08939v2 |
http://arxiv.org/pdf/1805.08939v2.pdf | |
PWC | https://paperswithcode.com/paper/approximate-random-dropout |
Repo | |
Framework | |
Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory
Title | Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory |
Authors | Jianyi Zhang, Ruiyi Zhang, Lawrence Carin, Changyou Chen |
Abstract | Particle-optimization-based sampling (POS) is a recently developed effective sampling technique that interactively updates a set of particles. A representative algorithm is the Stein variational gradient descent (SVGD). We prove, under certain conditions, SVGD experiences a theoretical pitfall, {\it i.e.}, particles tend to collapse. As a remedy, we generalize POS to a stochastic setting by injecting random noise into particle updates, thus yielding particle-optimization sampling (SPOS). Notably, for the first time, we develop {\em non-asymptotic convergence theory} for the SPOS framework (related to SVGD), characterizing algorithm convergence in terms of the 1-Wasserstein distance w.r.t.! the numbers of particles and iterations. Somewhat surprisingly, with the same number of updates (not too large) for each particle, our theory suggests adopting more particles does not necessarily lead to a better approximation of a target distribution, due to limited computational budget and numerical errors. This phenomenon is also observed in SVGD and verified via an experiment on synthetic data. Extensive experimental results verify our theory and demonstrate the effectiveness of our proposed framework. |
Tasks | |
Published | 2018-09-05 |
URL | https://arxiv.org/abs/1809.01293v5 |
https://arxiv.org/pdf/1809.01293v5.pdf | |
PWC | https://paperswithcode.com/paper/stochastic-particle-optimization-sampling-and |
Repo | |
Framework | |
A Structure-aware Online Learning Algorithm for Markov Decision Processes
Title | A Structure-aware Online Learning Algorithm for Markov Decision Processes |
Authors | Arghyadip Roy, Vivek Borkar, Abhay Karandikar, Prasanna Chaporkar |
Abstract | To overcome the curse of dimensionality and curse of modeling in Dynamic Programming (DP) methods for solving classical Markov Decision Process (MDP) problems, Reinforcement Learning (RL) algorithms are popular. In this paper, we consider an infinite-horizon average reward MDP problem and prove the optimality of the threshold policy under certain conditions. Traditional RL techniques do not exploit the threshold nature of optimal policy while learning. In this paper, we propose a new RL algorithm which utilizes the known threshold structure of the optimal policy while learning by reducing the feasible policy space. We establish that the proposed algorithm converges to the optimal policy. It provides a significant improvement in convergence speed and computational and storage complexity over traditional RL algorithms. The proposed technique can be applied to a wide variety of optimization problems that include energy efficient data transmission and management of queues. We exhibit the improvement in convergence speed of the proposed algorithm over other RL algorithms through simulations. |
Tasks | |
Published | 2018-11-28 |
URL | http://arxiv.org/abs/1811.11646v1 |
http://arxiv.org/pdf/1811.11646v1.pdf | |
PWC | https://paperswithcode.com/paper/a-structure-aware-online-learning-algorithm |
Repo | |
Framework | |
Focused Hierarchical RNNs for Conditional Sequence Processing
Title | Focused Hierarchical RNNs for Conditional Sequence Processing |
Authors | Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni, Zhouhan Lin, Adam Trischler, Yoshua Bengio, Joelle Pineau, Laurent Charlin, Chris Pal |
Abstract | Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most of these models use a simple form of encoder with attention that looks over the entire sequence and assigns a weight to each token independently. We present a mechanism for focusing RNN encoders for sequence modelling tasks which allows them to attend to key parts of the input as needed. We formulate this using a multi-layer conditional sequence encoder that reads in one token at a time and makes a discrete decision on whether the token is relevant to the context or question being asked. The discrete gating mechanism takes in the context embedding and the current hidden state as inputs and controls information flow into the layer above. We train it using policy gradient methods. We evaluate this method on several types of tasks with different attributes. First, we evaluate the method on synthetic tasks which allow us to evaluate the model for its generalization ability and probe the behavior of the gates in more controlled settings. We then evaluate this approach on large scale Question Answering tasks including the challenging MS MARCO and SearchQA tasks. Our models shows consistent improvements for both tasks over prior work and our baselines. It has also shown to generalize significantly better on synthetic tasks as compared to the baselines. |
Tasks | Open-Domain Question Answering, Policy Gradient Methods, Question Answering |
Published | 2018-06-12 |
URL | http://arxiv.org/abs/1806.04342v1 |
http://arxiv.org/pdf/1806.04342v1.pdf | |
PWC | https://paperswithcode.com/paper/focused-hierarchical-rnns-for-conditional |
Repo | |
Framework | |
The challenge of simultaneous object detection and pose estimation: a comparative study
Title | The challenge of simultaneous object detection and pose estimation: a comparative study |
Authors | Daniel Oñoro-Rubio, Roberto J. López-Sastre, Carolina Redondo-Cabrera, Pedro Gil-Jiménez |
Abstract | Detecting objects and estimating their pose remains as one of the major challenges of the computer vision research community. There exists a compromise between localizing the objects and estimating their viewpoints. The detector ideally needs to be view-invariant, while the pose estimation process should be able to generalize towards the category-level. This work is an exploration of using deep learning models for solving both problems simultaneously. For doing so, we propose three novel deep learning architectures, which are able to perform a joint detection and pose estimation, where we gradually decouple the two tasks. We also investigate whether the pose estimation problem should be solved as a classification or regression problem, being this still an open question in the computer vision community. We detail a comparative analysis of all our solutions and the methods that currently define the state of the art for this problem. We use PASCAL3D+ and ObjectNet3D datasets to present the thorough experimental evaluation and main results. With the proposed models we achieve the state-of-the-art performance in both datasets. |
Tasks | Object Detection, Pose Estimation |
Published | 2018-01-24 |
URL | http://arxiv.org/abs/1801.08110v1 |
http://arxiv.org/pdf/1801.08110v1.pdf | |
PWC | https://paperswithcode.com/paper/the-challenge-of-simultaneous-object |
Repo | |
Framework | |
Enhanced Expressive Power and Fast Training of Neural Networks by Random Projections
Title | Enhanced Expressive Power and Fast Training of Neural Networks by Random Projections |
Authors | Jian-Feng Cai, Dong Li, Jiaze Sun, Ke Wang |
Abstract | Random projections are able to perform dimension reduction efficiently for datasets with nonlinear low-dimensional structures. One well-known example is that random matrices embed sparse vectors into a low-dimensional subspace nearly isometrically, known as the restricted isometric property in compressed sensing. In this paper, we explore some applications of random projections in deep neural networks. We provide the expressive power of fully connected neural networks when the input data are sparse vectors or form a low-dimensional smooth manifold. We prove that the number of neurons required for approximating a Lipschitz function with a prescribed precision depends on the sparsity or the dimension of the manifold and weakly on the dimension of the input vector. The key in our proof is that random projections embed stably the set of sparse vectors or a low-dimensional smooth manifold into a low-dimensional subspace. Based on this fact, we also propose some new neural network models, where at each layer the input is first projected onto a low-dimensional subspace by a random projection and then the standard linear connection and non-linear activation are applied. In this way, the number of parameters in neural networks is significantly reduced, and therefore the training of neural networks can be accelerated without too much performance loss. |
Tasks | Dimensionality Reduction |
Published | 2018-11-22 |
URL | http://arxiv.org/abs/1811.09054v2 |
http://arxiv.org/pdf/1811.09054v2.pdf | |
PWC | https://paperswithcode.com/paper/enhanced-expressive-power-and-fast-training |
Repo | |
Framework | |
The External Interface for Extending WASP
Title | The External Interface for Extending WASP |
Authors | Carmine Dodaro, Francesco Ricca |
Abstract | Answer set programming (ASP) is a successful declarative formalism for knowledge representation and reasoning. The evaluation of ASP programs is nowadays based on the Conflict-Driven Clause Learning (CDCL) backtracking search algorithm. Recent work suggested that the performance of CDCL-based implementations can be considerably improved on specific benchmarks by extending their solving capabilities with custom heuristics and propagators. However, embedding such algorithms into existing systems requires expert knowledge of the internals of ASP implementations. The development of effective solver extensions can be made easier by providing suitable programming interfaces. In this paper, we present the interface for extending the CDCL-based ASP solver WASP. The interface is both general, i.e. it can be used for providing either new branching heuristics and propagators, and external, i.e. the implementation of new algorithms requires no internal modifications of WASP. Moreover, we review the applications of the interface witnessing it can be successfully used to extend WASP for solving effectively hard instances of both real-world and synthetic problems. Under consideration in Theory and Practice of Logic Programming (TPLP). |
Tasks | |
Published | 2018-11-05 |
URL | http://arxiv.org/abs/1811.01692v2 |
http://arxiv.org/pdf/1811.01692v2.pdf | |
PWC | https://paperswithcode.com/paper/the-external-interface-for-extending-wasp |
Repo | |
Framework | |
Bitewing Radiography Semantic Segmentation Base on Conditional Generative Adversarial Nets
Title | Bitewing Radiography Semantic Segmentation Base on Conditional Generative Adversarial Nets |
Authors | Jiang Yun, Tan Ning, Zhang Hai, Peng Tingting |
Abstract | Currently, Segmentation of bitewing radiograpy images is a very challenging task. The focus of the study is to segment it into caries, enamel, dentin, pulp, crowns, restoration and root canal treatments. The main method of semantic segmentation of bitewing radiograpy images at this stage is the U-shaped deep convolution neural network, but its accuracy is low. in order to improve the accuracy of semantic segmentation of bitewing radiograpy images, this paper proposes the use of Conditional Generative Adversarial network (cGAN) combined with U-shaped network structure (U-Net) approach to semantic segmentation of bitewing radiograpy images. The experimental results show that the accuracy of cGAN combined with U-Net is 69.7%, which is 13.3% higher than the accuracy of u-shaped deep convolution neural network of 56.4%. |
Tasks | Semantic Segmentation |
Published | 2018-02-07 |
URL | http://arxiv.org/abs/1802.02571v1 |
http://arxiv.org/pdf/1802.02571v1.pdf | |
PWC | https://paperswithcode.com/paper/bitewing-radiography-semantic-segmentation |
Repo | |
Framework | |