Paper Group ANR 989
Short Term Load Forecasting Using Deep Neural Networks. Unsupervised Meta-Learning for Reinforcement Learning. Suggesting Cooking Recipes Through Simulation and Bayesian Optimization. High-confidence error estimates for learned value functions. Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Feat …
Short Term Load Forecasting Using Deep Neural Networks
Title | Short Term Load Forecasting Using Deep Neural Networks |
Authors | Faisal Mohammad, Ki Boem Lee, Young-Chon Kim |
Abstract | Electricity load forecasting plays an important role in the energy planning such as generation and distribution. However, the nonlinearity and dynamic uncertainties in the smart grid environment are the main obstacles in forecasting accuracy. Deep Neural Network (DNN) is a set of intelligent computational algorithms that provide a comprehensive solution for modelling a complicated nonlinear relationship between the input and output through multiple hidden layers. In this paper, we propose DNN based electricity load forecasting system to manage the energy consumption in an efficient manner. We investigate the applicability of two deep neural network architectures Feed-forward Deep Neural Network (Deep-FNN) and Recurrent Deep Neural Network (Deep-RNN) to the New York Independent System Operator (NYISO) electricity load forecasting task. We test our algorithm with various activation functions such as Sigmoid, Hyperbolic Tangent (tanh) and Rectifier Linear Unit (ReLU). The performance measurement of two network architectures is compared in terms of Mean Absolute Percentage Error (MAPE) metric. |
Tasks | Load Forecasting |
Published | 2018-11-08 |
URL | http://arxiv.org/abs/1811.03242v1 |
http://arxiv.org/pdf/1811.03242v1.pdf | |
PWC | https://paperswithcode.com/paper/short-term-load-forecasting-using-deep-neural |
Repo | |
Framework | |
Unsupervised Meta-Learning for Reinforcement Learning
Title | Unsupervised Meta-Learning for Reinforcement Learning |
Authors | Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine |
Abstract | Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depends on the tasks available for meta-training: in the same way that supervised learning generalizes best to test points drawn from the same distribution as the training points, meta-learning methods generalize best to tasks from the same distribution as the meta-training tasks. In effect, meta-reinforcement learning offloads the design burden from algorithm design to task design. If we can automate the process of task design as well, we can devise a meta-learning algorithm that is truly automated. In this work, we take a step in this direction, proposing a family of unsupervised meta-learning algorithms for reinforcement learning. We motivate and describe a general recipe for unsupervised meta-reinforcement learning, and present an instantiation of this approach. Our conceptual and theoretical contributions consist of formulating the unsupervised meta-reinforcement learning problem and describing how task proposals based on mutual information can be used to train optimal meta-learners. Our experimental results indicate that unsupervised meta-reinforcement learning effectively acquires accelerated reinforcement learning procedures without the need for manual task design and these procedures exceed the performance of learning from scratch. |
Tasks | Meta-Learning, Multi-Task Learning |
Published | 2018-06-12 |
URL | https://arxiv.org/abs/1806.04640v2 |
https://arxiv.org/pdf/1806.04640v2.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-meta-learning-for-reinforcement |
Repo | |
Framework | |
Suggesting Cooking Recipes Through Simulation and Bayesian Optimization
Title | Suggesting Cooking Recipes Through Simulation and Bayesian Optimization |
Authors | Eduardo C. Garrido-Merchán, Alejandro Albarca-Molina |
Abstract | Cooking typically involves a plethora of decisions about ingredients and tools that need to be chosen in order to write a good cooking recipe. Cooking can be modelled in an optimization framework, as it involves a search space of ingredients, kitchen tools, cooking times or temperatures. If we model as an objective function the quality of the recipe, several problems arise. No analytical expression can model all the recipes, so no gradients are available. The objective function is subjective, in other words, it contains noise. Moreover, evaluations are expensive both in time and human resources. Bayesian Optimization (BO) emerges as an ideal methodology to tackle problems with these characteristics. In this paper, we propose a methodology to suggest recipe recommendations based on a Machine Learning (ML) model that fits real and simulated data and BO. We provide empirical evidence with two experiments that support the adequacy of the methodology. |
Tasks | |
Published | 2018-11-09 |
URL | http://arxiv.org/abs/1811.03868v1 |
http://arxiv.org/pdf/1811.03868v1.pdf | |
PWC | https://paperswithcode.com/paper/suggesting-cooking-recipes-through-simulation |
Repo | |
Framework | |
High-confidence error estimates for learned value functions
Title | High-confidence error estimates for learned value functions |
Authors | Touqir Sajed, Wesley Chung, Martha White |
Abstract | Estimating the value function for a fixed policy is a fundamental problem in reinforcement learning. Policy evaluation algorithms—to estimate value functions—continue to be developed, to improve convergence rates, improve stability and handle variability, particularly for off-policy learning. To understand the properties of these algorithms, the experimenter needs high-confidence estimates of the accuracy of the learned value functions. For environments with small, finite state-spaces, like chains, the true value function can be easily computed, to compute accuracy. For large, or continuous state-spaces, however, this is no longer feasible. In this paper, we address the largely open problem of how to obtain these high-confidence estimates, for general state-spaces. We provide a high-confidence bound on an empirical estimate of the value error to the true value error. We use this bound to design an offline sampling algorithm, which stores the required quantities to repeatedly compute value error estimates for any learned value function. We provide experiments investigating the number of samples required by this offline algorithm in simple benchmark reinforcement learning domains, and highlight that there are still many open questions to be solved for this important problem. |
Tasks | |
Published | 2018-08-28 |
URL | http://arxiv.org/abs/1808.09127v1 |
http://arxiv.org/pdf/1808.09127v1.pdf | |
PWC | https://paperswithcode.com/paper/high-confidence-error-estimates-for-learned |
Repo | |
Framework | |
Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features
Title | Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features |
Authors | Sharath Adavanne, Archontis Politis, Tuomas Virtanen |
Abstract | In this paper, we propose a stacked convolutional and recurrent neural network (CRNN) with a 3D convolutional neural network (CNN) in the first layer for the multichannel sound event detection (SED) task. The 3D CNN enables the network to simultaneously learn the inter- and intra-channel features from the input multichannel audio. In order to evaluate the proposed method, multichannel audio datasets with different number of overlapping sound sources are synthesized. Each of this dataset has a four-channel first-order Ambisonic, binaural, and single-channel versions, on which the performance of SED using the proposed method are compared to study the potential of SED using multichannel audio. A similar study is also done with the binaural and single-channel versions of the real-life recording TUT-SED 2017 development dataset. The proposed method learns to recognize overlapping sound events from multichannel features faster and performs better SED with a fewer number of training epochs. The results show that on using multichannel Ambisonic audio in place of single-channel audio we improve the overall F-score by 7.5%, overall error rate by 10% and recognize 15.6% more sound events in time frames with four overlapping sound sources. |
Tasks | Sound Event Detection |
Published | 2018-01-29 |
URL | http://arxiv.org/abs/1801.09522v1 |
http://arxiv.org/pdf/1801.09522v1.pdf | |
PWC | https://paperswithcode.com/paper/multichannel-sound-event-detection-using-3d |
Repo | |
Framework | |
Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks
Title | Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks |
Authors | Tobias Hinz, Nicolás Navarro-Guerrero, Sven Magg, Stefan Wermter |
Abstract | Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional representation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher-dimensional data. We compare this approach with the standard procedure of optimizing the hyperparameters only on the original input. We perform experiments with various state-of-the-art hyperparameter optimization algorithms such as random search, the tree of parzen estimators (TPEs), sequential model-based algorithm configuration (SMAC), and a genetic algorithm (GA). Our experiments indicate that it is possible to speed up the optimization process by using lower-dimensional data representations at the beginning, while increasing the dimensionality of the input later in the optimization process. This is independent of the underlying optimization procedure, making the approach promising for many existing hyperparameter optimization algorithms. |
Tasks | Hyperparameter Optimization |
Published | 2018-07-19 |
URL | http://arxiv.org/abs/1807.07362v1 |
http://arxiv.org/pdf/1807.07362v1.pdf | |
PWC | https://paperswithcode.com/paper/speeding-up-the-hyperparameter-optimization |
Repo | |
Framework | |
Multi-label Classification of Surgical Tools with Convolutional Neural Networks
Title | Multi-label Classification of Surgical Tools with Convolutional Neural Networks |
Authors | Jonas Prellberg, Oliver Kramer |
Abstract | Automatic tool detection from surgical imagery has a multitude of useful applications, such as real-time computer assistance for the surgeon. Using the successful residual network architecture, a system that can distinguish 21 different tools in cataract surgery videos is created. The videos are provided as part of the 2017 CATARACTS challenge and pose difficulties found in many real-world datasets, for example a strong class imbalance. The construction of the detection system is guided by a wide array of experiments that explore different design decisions. |
Tasks | Multi-Label Classification |
Published | 2018-05-15 |
URL | http://arxiv.org/abs/1805.05760v1 |
http://arxiv.org/pdf/1805.05760v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-label-classification-of-surgical-tools |
Repo | |
Framework | |
Style Transfer Through Multilingual and Feedback-Based Back-Translation
Title | Style Transfer Through Multilingual and Feedback-Based Back-Translation |
Authors | Shrimai Prabhumoye, Yulia Tsvetkov, Alan W Black, Ruslan Salakhutdinov |
Abstract | Style transfer is the task of transferring an attribute of a sentence (e.g., formality) while maintaining its semantic content. The key challenge in style transfer is to strike a balance between the competing goals, one to preserve meaning and the other to improve the style transfer accuracy. Prior research has identified that the task of meaning preservation is generally harder to attain and evaluate. This paper proposes two extensions of the state-of-the-art style transfer models aiming at improving the meaning preservation in style transfer. Our evaluation shows that these extensions help to ground meaning better while improving the transfer accuracy. |
Tasks | Style Transfer |
Published | 2018-09-17 |
URL | http://arxiv.org/abs/1809.06284v1 |
http://arxiv.org/pdf/1809.06284v1.pdf | |
PWC | https://paperswithcode.com/paper/style-transfer-through-multilingual-and |
Repo | |
Framework | |
Boundary Evolution Algorithm for SAT-NP
Title | Boundary Evolution Algorithm for SAT-NP |
Authors | Zhaoyang Ai, Chaodong Fan, Yingjie Zhang, Huigui Rong, Ze’an Tian, Haibing Fu |
Abstract | A boundary evolution Algorithm (BEA) is proposed by simultaneously taking into account the bottom and the high-level crossover and mutation, ie., the boundary of the hierarchical genetic algorithm. Operators and optimal individuals based on optional annealing are designed. Based on the numerous versions of genetic algorithm, the boundary evolution approach with crossover and mutation has been tested on the SAT problem and compared with two competing methods: a traditional genetic algorithm and another traditional hierarchical genetic algorithm, and among some others. The results of the comparative experiments in solving SAT problem have proved that the new hierarchical genetic algorithm based on simulated annealing and optimal individuals (BEA) can improve the success rate and convergence speed considerably for SAT problem due to its avoidance of both divergence and loss of optimal individuals, and by coronary, conducive to NP problem. Though more extensive comparisons are to be made on more algorithms, the consideration of the boundary elasticity of hierarchical genetic algorithm is an implication of evolutionary algorithm. |
Tasks | |
Published | 2018-12-22 |
URL | http://arxiv.org/abs/1903.01894v1 |
http://arxiv.org/pdf/1903.01894v1.pdf | |
PWC | https://paperswithcode.com/paper/boundary-evolution-algorithm-for-sat-np |
Repo | |
Framework | |
PotentialNet for Molecular Property Prediction
Title | PotentialNet for Molecular Property Prediction |
Authors | Evan N. Feinberg, Debnil Sur, Zhenqin Wu, Brooke E. Husic, Huanghao Mai, Yang Li, Saisai Sun, Jianyi Yang, Bharath Ramsundar, Vijay S. Pande |
Abstract | The arc of drug discovery entails a multiparameter optimization problem spanning vast length scales. They key parameters range from solubility (angstroms) to protein-ligand binding (nanometers) to in vivo toxicity (meters). Through feature learning—instead of feature engineering—deep neural networks promise to outperform both traditional physics-based and knowledge-based machine learning models for predicting molecular properties pertinent to drug discovery. To this end, we present the PotentialNet family of graph convolutions. These models are specifically designed for and achieve state-of-the-art performance for protein-ligand binding affinity. We further validate these deep neural networks by setting new standards of performance in several ligand-based tasks. In parallel, we introduce a new metric, the Regression Enrichment Factor $EF_\chi^{(R)}$, to measure the early enrichment of computational models for chemical data. Finally, we introduce a cross-validation strategy based on structural homology clustering that can more accurately measure model generalizability, which crucially distinguishes the aims of machine learning for drug discovery from standard machine learning tasks. |
Tasks | Drug Discovery, Feature Engineering, Molecular Property Prediction |
Published | 2018-03-12 |
URL | http://arxiv.org/abs/1803.04465v2 |
http://arxiv.org/pdf/1803.04465v2.pdf | |
PWC | https://paperswithcode.com/paper/potentialnet-for-molecular-property |
Repo | |
Framework | |
Comparing Models of Associative Meaning: An Empirical Investigation of Reference in Simple Language Games
Title | Comparing Models of Associative Meaning: An Empirical Investigation of Reference in Simple Language Games |
Authors | Judy Hanwen Shen, Matthias Hofer, Bjarke Felbo, Roger Levy |
Abstract | Simple reference games are of central theoretical and empirical importance in the study of situated language use. Although language provides rich, compositional truth-conditional semantics to facilitate reference, speakers and listeners may sometimes lack the overall lexical and cognitive resources to guarantee successful reference through these means alone. However, language also has rich associational structures that can serve as a further resource for achieving successful reference. Here we investigate this use of associational information in a setting where only associational information is available: a simplified version of the popular game Codenames. Using optimal experiment design techniques, we compare a range of models varying in the type of associative information deployed and in level of pragmatic sophistication against human behavior. In this setting, we find that listeners’ behavior reflects direct bigram collocational associations more strongly than word-embedding or semantic knowledge graph-based associations and that there is little evidence for pragmatically sophisticated behavior by either speakers or listeners of the type that might be predicted by recursive-reasoning models such as the Rational Speech Acts theory. These results shed light on the nature of the lexical resources that speakers and listeners can bring to bear in achieving reference through associative meaning alone. |
Tasks | |
Published | 2018-10-08 |
URL | http://arxiv.org/abs/1810.03717v1 |
http://arxiv.org/pdf/1810.03717v1.pdf | |
PWC | https://paperswithcode.com/paper/comparing-models-of-associative-meaning-an |
Repo | |
Framework | |
C2A: Crowd Consensus Analytics for Virtual Colonoscopy
Title | C2A: Crowd Consensus Analytics for Virtual Colonoscopy |
Authors | Ji Hwan Park, Saad Nadeem, Seyedkoosha Mirhosseini, Arie Kaufman |
Abstract | We present a medical crowdsourcing visual analytics platform called C{$^2$}A to visualize, classify and filter crowdsourced clinical data. More specifically, C$^2$A is used to build consensus on a clinical diagnosis by visualizing crowd responses and filtering out anomalous activity. Crowdsourcing medical applications have recently shown promise where the non-expert users (the crowd) were able to achieve accuracy similar to the medical experts. This has the potential to reduce interpretation/reading time and possibly improve accuracy by building a consensus on the findings beforehand and letting the medical experts make the final diagnosis. In this paper, we focus on a virtual colonoscopy (VC) application with the clinical technicians as our target users, and the radiologists acting as consultants and classifying segments as benign or malignant. In particular, C$^2$A is used to analyze and explore crowd responses on video segments, created from fly-throughs in the virtual colon. C$^2$A provides several interactive visualization components to build crowd consensus on video segments, to detect anomalies in the crowd data and in the VC video segments, and finally, to improve the non-expert user’s work quality and performance by A/B testing for the optimal crowdsourcing platform and application-specific parameters. Case studies and domain experts feedback demonstrate the effectiveness of our framework in improving workers’ output quality, the potential to reduce the radiologists’ interpretation time, and hence, the potential to improve the traditional clinical workflow by marking the majority of the video segments as benign based on the crowd consensus. |
Tasks | |
Published | 2018-10-21 |
URL | http://arxiv.org/abs/1810.09012v1 |
http://arxiv.org/pdf/1810.09012v1.pdf | |
PWC | https://paperswithcode.com/paper/c2a-crowd-consensus-analytics-for-virtual |
Repo | |
Framework | |
Etymo: A New Discovery Engine for AI Research
Title | Etymo: A New Discovery Engine for AI Research |
Authors | Weijian Zhang, Jonathan Deakin, Nicholas J. Higham, Shuaiqiang Wang |
Abstract | We present Etymo (https://etymo.io), a discovery engine to facilitate artificial intelligence (AI) research and development. It aims to help readers navigate a large number of AI-related papers published every week by using a novel form of search that finds relevant papers and displays related papers in a graphical interface. Etymo constructs and maintains an adaptive similarity-based network of research papers as an all-purpose knowledge graph for ranking, recommendation, and visualisation. The network is constantly evolving and can learn from user feedback to adjust itself. |
Tasks | |
Published | 2018-01-25 |
URL | http://arxiv.org/abs/1801.08573v1 |
http://arxiv.org/pdf/1801.08573v1.pdf | |
PWC | https://paperswithcode.com/paper/etymo-a-new-discovery-engine-for-ai-research |
Repo | |
Framework | |
Pedestrian Trajectory Prediction with Structured Memory Hierarchies
Title | Pedestrian Trajectory Prediction with Structured Memory Hierarchies |
Authors | Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes |
Abstract | This paper presents a novel framework for human trajectory prediction based on multimodal data (video and radar). Motivated by recent neuroscience discoveries, we propose incorporating a structured memory component in the human trajectory prediction pipeline to capture historical information to improve performance. We introduce structured LSTM cells for modelling the memory content hierarchically, preserving the spatiotemporal structure of the information and enabling us to capture both short-term and long-term context. We demonstrate how this architecture can be extended to integrate salient information from multiple modalities to automatically store and retrieve important information for decision making without any supervision. We evaluate the effectiveness of the proposed models on a novel multimodal dataset that we introduce, consisting of 40,000 pedestrian trajectories, acquired jointly from a radar system and a CCTV camera system installed in a public place. The performance is also evaluated on the publicly available New York Grand Central pedestrian database. In both settings, the proposed models demonstrate their capability to better anticipate future pedestrian motion compared to existing state of the art. |
Tasks | Decision Making, Trajectory Prediction |
Published | 2018-07-22 |
URL | http://arxiv.org/abs/1807.08381v1 |
http://arxiv.org/pdf/1807.08381v1.pdf | |
PWC | https://paperswithcode.com/paper/pedestrian-trajectory-prediction-with |
Repo | |
Framework | |
PRED18: Dataset and Further Experiments with DAVIS Event Camera in Predator-Prey Robot Chasing
Title | PRED18: Dataset and Further Experiments with DAVIS Event Camera in Predator-Prey Robot Chasing |
Authors | Diederik Paul Moeys, Daniel Neil, Federico Corradi, Emmett Kerr, Philip Vance, Gautham Das, Sonya A. Coleman, Thomas M. McGinnity, Dermot Kerr, Tobi Delbruck |
Abstract | Machine vision systems using convolutional neural networks (CNNs) for robotic applications are increasingly being developed. Conventional vision CNNs are driven by camera frames at constant sample rate, thus achieving a fixed latency and power consumption tradeoff. This paper describes further work on the first experiments of a closed-loop robotic system integrating a CNN together with a Dynamic and Active Pixel Vision Sensor (DAVIS) in a predator/prey scenario. The DAVIS, mounted on the predator Summit XL robot, produces frames at a fixed 15 Hz frame-rate and Dynamic Vision Sensor (DVS) histograms containing 5k ON and OFF events at a variable frame-rate ranging from 15-500 Hz depending on the robot speeds. In contrast to conventional frame-based systems, the latency and processing cost depends on the rate of change of the image. The CNN is trained offline on the 1.25h labeled dataset to recognize the position and size of the prey robot, in the field of view of the predator. During inference, combining the ten output classes of the CNN allows extracting the analog position vector of the prey relative to the predator with a mean 8.7% error in angular estimation. The system is compatible with conventional deep learning technology, but achieves a variable latency-power tradeoff that adapts automatically to the dynamics. Finally, investigations on the robustness of the algorithm, a human performance comparison and a deconvolution analysis are also explored. |
Tasks | |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.03128v1 |
http://arxiv.org/pdf/1807.03128v1.pdf | |
PWC | https://paperswithcode.com/paper/pred18-dataset-and-further-experiments-with |
Repo | |
Framework | |