July 28, 2019

2605 words 13 mins read

Paper Group ANR 329

Maximum Margin Interval Trees. Learning Hierarchical Information Flow with Recurrent Neural Modules. The detour problem in a stochastic environment: Tolman revisited. Interstitial Content Detection. Soft Biometrics: Gender Recognition from Unconstrained Face Images using Local Feature Descriptor. Cold-Start Reinforcement Learning with Softmax Polic …

Maximum Margin Interval Trees


Title	Maximum Margin Interval Trees
Authors	Alexandre Drouin, Toby Dylan Hocking, François Laviolette
Abstract	Learning a regression function using censored or interval-valued output data is an important problem in fields such as genomics and medicine. The goal is to learn a real-valued prediction function, and the training output labels indicate an interval of possible values. Whereas most existing algorithms for this task are linear models, in this paper we investigate learning nonlinear tree models. We propose to learn a tree by minimizing a margin-based discriminative objective function, and we provide a dynamic programming algorithm for computing the optimal solution in log-linear time. We show empirically that this algorithm achieves state-of-the-art speed and prediction accuracy in a benchmark of several data sets.
Tasks
Published	2017-10-11
URL	http://arxiv.org/abs/1710.04234v2
PDF	http://arxiv.org/pdf/1710.04234v2.pdf
PWC	https://paperswithcode.com/paper/maximum-margin-interval-trees
Repo
Framework

Learning Hierarchical Information Flow with Recurrent Neural Modules


Title	Learning Hierarchical Information Flow with Recurrent Neural Modules
Authors	Danijar Hafner, Alex Irpan, James Davidson, Nicolas Heess
Abstract	We propose ThalNet, a deep learning model inspired by neocortical communication via the thalamus. Our model consists of recurrent neural modules that send features through a routing center, endowing the modules with the flexibility to share features over multiple time steps. We show that our model learns to route information hierarchically, processing input data by a chain of modules. We observe common architectures, such as feed forward neural networks and skip connections, emerging as special cases of our architecture, while novel connectivity patterns are learned for the text8 compression task. Our model outperforms standard recurrent neural networks on several sequential benchmarks.
Tasks
Published	2017-06-18
URL	http://arxiv.org/abs/1706.05744v2
PDF	http://arxiv.org/pdf/1706.05744v2.pdf
PWC	https://paperswithcode.com/paper/learning-hierarchical-information-flow-with
Repo
Framework

The detour problem in a stochastic environment: Tolman revisited


Title	The detour problem in a stochastic environment: Tolman revisited
Authors	Pegah Fakhari, Arash Khodadadi, Jerome Busemeyer
Abstract	We designed a grid world task to study human planning and re-planning behavior in an unknown stochastic environment. In our grid world, participants were asked to travel from a random starting point to a random goal position while maximizing their reward. Because they were not familiar with the environment, they needed to learn its characteristics from experience to plan optimally. Later in the task, we randomly blocked the optimal path to investigate whether and how people adjust their original plans to find a detour. To this end, we developed and compared 12 different models. These models were different on how they learned and represented the environment and how they planned to catch the goal. The majority of our participants were able to plan optimally. We also showed that people were capable of revising their plans when an unexpected event occurred. The result from the model comparison showed that the model-based reinforcement learning approach provided the best account for the data and outperformed heuristics in explaining the behavioral data in the re-planning trials.
Tasks
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09761v1
PDF	http://arxiv.org/pdf/1709.09761v1.pdf
PWC	https://paperswithcode.com/paper/the-detour-problem-in-a-stochastic
Repo
Framework

Interstitial Content Detection


Title	Interstitial Content Detection
Authors	Elizabeth Lucas
Abstract	Interstitial content is online content which grays out, or otherwise obscures the main page content. In this technical report, we discuss exploratory research into detecting the presence of interstitial content in web pages. We discuss the use of computer vision techniques to detect interstitials, and the potential use of these techniques to provide a labelled dataset for machine learning.
Tasks
Published	2017-08-13
URL	http://arxiv.org/abs/1708.04879v1
PDF	http://arxiv.org/pdf/1708.04879v1.pdf
PWC	https://paperswithcode.com/paper/interstitial-content-detection
Repo
Framework

Soft Biometrics: Gender Recognition from Unconstrained Face Images using Local Feature Descriptor


Title	Soft Biometrics: Gender Recognition from Unconstrained Face Images using Local Feature Descriptor
Authors	Olasimbo Ayodeji Arigbabu, Sharifah Mumtazah Syed Ahmad, Wan Azizun Wan Adnan, Salman Yussof, Saif Mahmood
Abstract	Gender recognition from unconstrained face images is a challenging task due to the high degree of misalignment, pose, expression, and illumination variation. In previous works, the recognition of gender from unconstrained face images is approached by utilizing image alignment, exploiting multiple samples per individual to improve the learning ability of the classifier, or learning gender based on prior knowledge about pose and demographic distributions of the dataset. However, image alignment increases the complexity and time of computation, while the use of multiple samples or having prior knowledge about data distribution is unrealistic in practical applications. This paper presents an approach for gender recognition from unconstrained face images. Our technique exploits the robustness of local feature descriptor to photometric variations to extract the shape description of the 2D face image using a single sample image per individual. The results obtained from experiments on Labeled Faces in the Wild (LFW) dataset describe the effectiveness of the proposed method. The essence of this study is to investigate the most suitable functions and parameter settings for recognizing gender from unconstrained face images.
Tasks
Published	2017-02-08
URL	http://arxiv.org/abs/1702.02537v1
PDF	http://arxiv.org/pdf/1702.02537v1.pdf
PWC	https://paperswithcode.com/paper/soft-biometrics-gender-recognition-from
Repo
Framework

Cold-Start Reinforcement Learning with Softmax Policy Gradient


Title	Cold-Start Reinforcement Learning with Softmax Policy Gradient
Authors	Nan Ding, Radu Soricut
Abstract	Policy-gradient approaches to reinforcement learning have two common and undesirable overhead procedures, namely warm-start training and sample variance reduction. In this paper, we describe a reinforcement learning method based on a softmax value function that requires neither of these procedures. Our method combines the advantages of policy-gradient methods with the efficiency and simplicity of maximum-likelihood approaches. We apply this new cold-start reinforcement learning method in training sequence generation models for structured output prediction problems. Empirical evidence validates this method on automatic summarization and image captioning tasks.
Tasks	Image Captioning, Policy Gradient Methods
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09346v2
PDF	http://arxiv.org/pdf/1709.09346v2.pdf
PWC	https://paperswithcode.com/paper/cold-start-reinforcement-learning-with
Repo
Framework

Fast camera focus estimation for gaze-based focus control


Title	Fast camera focus estimation for gaze-based focus control
Authors	Wolfgang Fuhl, Thiago Santini, Enkelejda Kasneci
Abstract	Many cameras implement auto-focus functionality. However, they typically require the user to manually identify the location to be focused on. While such an approach works for temporally-sparse autofocusing functionality (e.g., photo shooting), it presents extreme usability problems when the focus must be quickly switched between multiple areas (and depths) of interest - e.g., in a gaze-based autofocus approach. This work introduces a novel, real-time auto-focus approach based on eye-tracking, which enables the user to shift the camera focus plane swiftly based solely on the gaze information. Moreover, the proposed approach builds a graph representation of the image to estimate depth plane surfaces and runs in real time (requiring ~20ms on a single i5 core), thus allowing for the depth map estimation to be performed dynamically. We evaluated our algorithm for gaze-based depth estimation against state-of-the-art approaches based on eight new data sets with flat, skewed, and round surfaces, as well as publicly available datasets.
Tasks	Depth Estimation, Eye Tracking
Published	2017-11-09
URL	http://arxiv.org/abs/1711.03306v1
PDF	http://arxiv.org/pdf/1711.03306v1.pdf
PWC	https://paperswithcode.com/paper/fast-camera-focus-estimation-for-gaze-based
Repo
Framework

QoS-Aware Multi-Armed Bandits


Title	QoS-Aware Multi-Armed Bandits
Authors	Lenz Belzner, Thomas Gabor
Abstract	Motivated by runtime verification of QoS requirements in self-adaptive and self-organizing systems that are able to reconfigure their structure and behavior in response to runtime data, we propose a QoS-aware variant of Thompson sampling for multi-armed bandits. It is applicable in settings where QoS satisfaction of an arm has to be ensured with high confidence efficiently, rather than finding the optimal arm while minimizing regret. Preliminary experimental results encourage further research in the field of QoS-aware decision making.
Tasks	Decision Making, Multi-Armed Bandits
Published	2017-02-28
URL	http://arxiv.org/abs/1703.10669v1
PDF	http://arxiv.org/pdf/1703.10669v1.pdf
PWC	https://paperswithcode.com/paper/qos-aware-multi-armed-bandits
Repo
Framework

Decoupling “when to update” from “how to update”


Title	Decoupling “when to update” from “how to update”
Authors	Eran Malach, Shai Shalev-Shwartz
Abstract	Deep learning requires data. A useful approach to obtain data is to be creative and mine data from various sources, that were created for different purposes. Unfortunately, this approach often leads to noisy labels. In this paper, we propose a meta algorithm for tackling the noisy labels problem. The key idea is to decouple “when to update” from “how to update”. We demonstrate the effectiveness of our algorithm by mining data for gender classification by combining the Labeled Faces in the Wild (LFW) face recognition dataset with a textual genderizing service, which leads to a noisy dataset. While our approach is very simple to implement, it leads to state-of-the-art results. We analyze some convergence properties of the proposed algorithm.
Tasks	Face Recognition
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02613v2
PDF	http://arxiv.org/pdf/1706.02613v2.pdf
PWC	https://paperswithcode.com/paper/decoupling-when-to-update-from-how-to-update
Repo
Framework

Evolving Parsimonious Networks by Mixing Activation Functions


Title	Evolving Parsimonious Networks by Mixing Activation Functions
Authors	Alexander Hagg, Maximilian Mensing, Alexander Asteroth
Abstract	Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, which is important when training networks with a small number of samples. In this work we extend the neuroevolution algorithm NEAT to evolve the activation function of neurons in addition to the topology and weights of the network. The size and performance of networks produced using NEAT with uniform activation in all nodes, or homogenous networks, is compared to networks which contain a mixture of activation functions, or heterogenous networks. For a number of regression and classification benchmarks it is shown that, (1) qualitatively different activation functions lead to different results in homogeneous networks, (2) the heterogeneous version of NEAT is able to select well performing activation functions, (3) producing heterogeneous networks that are significantly smaller than homogeneous networks.
Tasks
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07122v1
PDF	http://arxiv.org/pdf/1703.07122v1.pdf
PWC	https://paperswithcode.com/paper/evolving-parsimonious-networks-by-mixing
Repo
Framework

A Resizable Mini-batch Gradient Descent based on a Multi-Armed Bandit


Title	A Resizable Mini-batch Gradient Descent based on a Multi-Armed Bandit
Authors	Seong Jin Cho, Sunghun Kang, Chang D. Yoo
Abstract	Determining the appropriate batch size for mini-batch gradient descent is always time consuming as it often relies on grid search. This paper considers a resizable mini-batch gradient descent (RMGD) algorithm based on a multi-armed bandit for achieving best performance in grid search by selecting an appropriate batch size at each epoch with a probability defined as a function of its previous success/failure. This probability encourages exploration of different batch size and then later exploitation of batch size with history of success. At each epoch, the RMGD samples a batch size from its probability distribution, then uses the selected batch size for mini-batch gradient descent. After obtaining the validation loss at each epoch, the probability distribution is updated to incorporate the effectiveness of the sampled batch size. The RMGD essentially assists the learning process to explore the possible domain of the batch size and exploit successful batch size. Experimental results show that the RMGD achieves performance better than the best performing single batch size. Furthermore, it, obviously, attains this performance in a shorter amount of time than grid search. It is surprising that the RMGD achieves better performance than grid search.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06424v3
PDF	http://arxiv.org/pdf/1711.06424v3.pdf
PWC	https://paperswithcode.com/paper/a-resizable-mini-batch-gradient-descent-based
Repo
Framework

Learning Image Relations with Contrast Association Networks


Title	Learning Image Relations with Contrast Association Networks
Authors	Yao Lu, Zhirong Yang, Juho Kannala, Samuel Kaski
Abstract	Inferring the relations between two images is an important class of tasks in computer vision. Examples of such tasks include computing optical flow and stereo disparity. We treat the relation inference tasks as a machine learning problem and tackle it with neural networks. A key to the problem is learning a representation of relations. We propose a new neural network module, contrast association unit (CAU), which explicitly models the relations between two sets of input variables. Due to the non-negativity of the weights in CAU, we adopt a multiplicative update algorithm for learning these weights. Experiments show that neural networks with CAUs are more effective in learning five fundamental image transformations than conventional neural networks.
Tasks	Optical Flow Estimation
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05665v2
PDF	http://arxiv.org/pdf/1705.05665v2.pdf
PWC	https://paperswithcode.com/paper/learning-image-relations-with-contrast
Repo
Framework

CNN Is All You Need


Title	CNN Is All You Need
Authors	Qiming Chen, Ren Wu
Abstract	The Convolution Neural Network (CNN) has demonstrated the unique advantage in audio, image and text learning; recently it has also challenged Recurrent Neural Networks (RNNs) with long short-term memory cells (LSTM) in sequence-to-sequence learning, since the computations involved in CNN are easily parallelizable whereas those involved in RNN are mostly sequential, leading to a performance bottleneck. However, unlike RNN, the native CNN lacks the history sensitivity required for sequence transformation; therefore enhancing the sequential order awareness, or position-sensitivity, becomes the key to make CNN the general deep learning model. In this work we introduce an extended CNN model with strengthen position-sensitivity, called PoseNet. A notable feature of PoseNet is the asymmetric treatment of position information in the encoder and the decoder. Experiments shows that PoseNet allows us to improve the accuracy of CNN based sequence-to-sequence learning significantly, achieving around 33-36 BLEU scores on the WMT 2014 English-to-German translation task, and around 44-46 BLEU scores on the English-to-French translation task.
Tasks
Published	2017-12-27
URL	http://arxiv.org/abs/1712.09662v1
PDF	http://arxiv.org/pdf/1712.09662v1.pdf
PWC	https://paperswithcode.com/paper/cnn-is-all-you-need
Repo
Framework

DNN-based uncertainty estimation for weighted DNN-HMM ASR


Title	DNN-based uncertainty estimation for weighted DNN-HMM ASR
Authors	José Novoa, Josué Fredes, Néstor Becerra Yoma
Abstract	In this paper, the uncertainty is defined as the mean square error between a given enhanced noisy observation vector and the corresponding clean one. Then, a DNN is trained by using enhanced noisy observation vectors as input and the uncertainty as output with a training database. In testing, the DNN receives an enhanced noisy observation vector and delivers the estimated uncertainty. This uncertainty in employed in combination with a weighted DNN-HMM based speech recognition system and compared with an existing estimation of the noise cancelling uncertainty variance based on an additive noise model. Experiments were carried out with Aurora-4 task. Results with clean, multi-noise and multi-condition training are presented.
Tasks	Speech Recognition
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10368v1
PDF	http://arxiv.org/pdf/1705.10368v1.pdf
PWC	https://paperswithcode.com/paper/dnn-based-uncertainty-estimation-for-weighted
Repo
Framework

Enabling Robots to Communicate their Objectives


Title	Enabling Robots to Communicate their Objectives
Authors	Sandy H. Huang, David Held, Pieter Abbeel, Anca D. Dragan
Abstract	The overarching goal of this work is to efficiently enable end-users to correctly anticipate a robot’s behavior in novel situations. Since a robot’s behavior is often a direct result of its underlying objective function, our insight is that end-users need to have an accurate mental model of this objective function in order to understand and predict what the robot will do. While people naturally develop such a mental model over time through observing the robot act, this familiarization process may be lengthy. Our approach reduces this time by having the robot model how people infer objectives from observed behavior, and then it selects those behaviors that are maximally informative. The problem of computing a posterior over objectives from observed behavior is known as Inverse Reinforcement Learning (IRL), and has been applied to robots learning human objectives. We consider the problem where the roles of human and robot are swapped. Our main contribution is to recognize that unlike robots, humans will not be exact in their IRL inference. We thus introduce two factors to define candidate approximate-inference models for human learning in this setting, and analyze them in a user study in the autonomous driving domain. We show that certain approximate-inference models lead to the robot generating example behaviors that better enable users to anticipate what it will do in novel situations. Our results also suggest, however, that additional research is needed in modeling how humans extrapolate from examples of robot behavior.
Tasks	Autonomous Driving
Published	2017-02-11
URL	http://arxiv.org/abs/1702.03465v2
PDF	http://arxiv.org/pdf/1702.03465v2.pdf
PWC	https://paperswithcode.com/paper/enabling-robots-to-communicate-their
Repo
Framework